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

    Neuronpedia

    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. 3760
    Prev
    Next
    INDEX
    Explanations

    information related to people's professional backgrounds and associations

    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
    314
    +0.13
    0.5%
    309
    +0.13
    0.5%
    115
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    -0.02
    326
    +0.13
    0.25
    556
    +0.12
    0.12
    Negative Logits
    oglu
    -0.77
     Woods
    -0.74
     reckoned
    -0.74
     disadvant
    -0.73
    isSpecialOrderable
    -0.70
     guaranteeing
    -0.69
     wel
    -0.69
     sworn
    -0.68
     abiding
    -0.65
     braking
    -0.64
    POSITIVE LOGITS
     alike
    1.18
    /,
    1.09
    /)
    1.09
     combo
    1.00
    /-
    0.92
    utterstock
    0.89
    terday
    0.85
    tenance
    0.85
    RF
    0.85
    /
    0.83
    Activations Density 10.591%

    No Known Activations