© 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. 40639
    Prev
    Next
    INDEX
    Explanations

    references to generic or non-specific terms or concepts

    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
    +0.18
    1.1%
    288
    +0.12
    0.7%
    302
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.19
    99
    +0.12
    0.10
    302
    +0.10
    0.10
    Negative Logits
    oir
    -0.59
    cano
    -0.59
    otos
    -0.53
    perty
    -0.52
    kers
    -0.52
    orah
    -0.51
    rero
    -0.51
    semb
    -0.50
    ¯¯
    -0.50
    tes
    -0.49
    POSITIVE LOGITS
    IFIC
    0.54
    ALLY
    0.54
    ization
    0.54
    ature
    0.53
     differentiation
    0.53
    isable
    0.51
     interchange
    0.51
     applic
    0.51
    ality
    0.50
     additive
    0.50
    Activations Density 6.355%

    No Known Activations