© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40319
    Prev
    Next
    INDEX
    Explanations

    terms related to writing, freelancing, and artistic endeavors

    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
    195
    +0.10
    0.6%
    721
    +0.07
    0.5%
    646
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.23
    195
    +0.07
    -0.01
    646
    +0.07
    0.06
    Negative Logits
    arium
    -0.62
    lda
    -0.61
    ighed
    -0.51
    bourg
    -0.49
    anamo
    -0.48
    stones
    -0.48
    erion
    -0.47
    aminer
    -0.47
     Doctrine
    -0.47
    metics
    -0.47
    POSITIVE LOGITS
    adic
    0.68
     intermittent
    0.65
     sporadic
    0.61
    luster
    0.57
     entreprene
    0.55
     erratic
    0.54
     unsuccessful
    0.54
    icably
    0.53
    lust
    0.53
     freel
    0.52
    Activations Density 10.536%

    No Known Activations