© 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. 32906
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions mentioned in the text

    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
    7
    +0.14
    0.6%
    597
    +0.11
    0.5%
    715
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.22
    7
    +0.11
    0.10
    496
    +0.11
    0.15
    Negative Logits
     reper
    -0.72
    bies
    -0.68
    cart
    -0.67
     Charter
    -0.66
     Journals
    -0.65
     Journal
    -0.64
     Harbor
    -0.64
     Directions
    -0.64
     Brunswick
    -0.64
    Journal
    -0.64
    POSITIVE LOGITS
    ally
    1.55
    ality
    1.51
    ately
    1.49
    ate
    1.48
    naire
    1.22
    als
    1.10
    elly
    1.05
    ates
    0.99
    bender
    0.99
    age
    0.99
    Activations Density 7.139%

    No Known Activations