© 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. 34735
    Prev
    Next
    INDEX
    Explanations

    pricing information

    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
    2
    +0.10
    0.6%
    481
    +0.10
    0.5%
    33
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.24
    6
    +0.10
    0.14
    2
    +0.08
    0.03
    Negative Logits
    omorphic
    -0.80
     Ada
    -0.63
    oreal
    -0.57
     abund
    -0.56
    farious
    -0.55
     rust
    -0.55
     lifeless
    -0.54
     caut
    -0.53
    ody
    -0.51
     Aval
    -0.51
    POSITIVE LOGITS
    mc
    0.71
    schild
    0.69
    AU
    0.64
    USD
    0.61
    month
    0.60
    pees
    0.60
    roman
    0.59
     Lifetime
    0.57
    fee
    0.57
    atari
    0.57
    Activations Density 7.807%

    No Known Activations