© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33334
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to similarities or comparisons between different situations, especially when discussing historical events or political situations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    672
    +0.13
    0.5%
    162
    +0.12
    0.4%
    677
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.13
    0.12
    393
    +0.12
    0.19
    598
    +0.11
    0.07
    Negative Logits
    *=-
    -0.91
    ase
    -0.88
    ä¿
    -0.85
    Frag
    -0.83
    icum
    -0.80
    76561
    -0.79
    Interstitial
    -0.79
    ases
    -0.78
    usa
    -0.78
    pac
    -0.77
    POSITIVE LOGITS
     thing
    1.19
     exact
    1.16
     vein
    1.13
     amount
    0.99
     kind
    0.99
     fate
    0.98
     playbook
    0.96
     reason
    0.91
     principle
    0.91
     sort
    0.91
    Activations Density 6.375%

    No Known Activations