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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33093
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth, increase, and improvement

    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
    447
    +0.20
    0.8%
    99
    +0.14
    0.6%
    603
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.20
    0.07
    554
    +0.14
    -0.10
    660
    +0.11
    0.07
    Negative Logits
     Portal
    -0.81
    rolled
    -0.78
    Ò
    -0.74
    yssey
    -0.72
    ------------------------------------------------
    -0.72
    cise
    -0.71
    portation
    -0.71
    opsis
    -0.70
    mination
    -0.70
    pn
    -0.70
    POSITIVE LOGITS
     Above
    0.88
     tides
    0.86
    ceed
    0.85
    xual
    0.84
    ocate
    0.84
    borough
    0.83
    rising
    0.81
    ups
    0.80
    water
    0.79
    mary
    0.79
    Activations Density 10.986%

    No Known Activations