© 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. 34719
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions for various recipes

    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
    +0.17
    0.8%
    288
    +0.16
    0.8%
    642
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.18
    128
    +0.16
    0.07
    699
    +0.12
    0.01
    Negative Logits
    vernment
    -0.96
    SPONSORED
    -0.68
    ostics
    -0.66
     Exile
    -0.66
    OPLE
    -0.65
     Gutenberg
    -0.65
     Centauri
    -0.65
     debtor
    -0.64
     Naz
    -0.62
    ļé
    -0.62
    POSITIVE LOGITS
    cream
    1.36
    flies
    1.16
    cup
    1.06
    beer
    1.01
    fat
    0.93
    nut
    0.92
    maid
    0.92
    riter
    0.91
    finger
    0.90
    bowl
    0.89
    Activations Density 6.314%

    No Known Activations