© 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. 34705
    Prev
    Next
    INDEX
    Explanations

    terms related to very popular, important or significant items or events

    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
    +0.11
    0.7%
    343
    +0.10
    0.6%
    554
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.21
    343
    +0.10
    0.08
    284
    +0.09
    0.09
    Negative Logits
    arettes
    -0.60
    chen
    -0.59
    sterdam
    -0.59
    elling
    -0.58
    odynam
    -0.58
    chens
    -0.58
    lah
    -0.58
    nee
    -0.57
    yang
    -0.57
    aret
    -0.57
    POSITIVE LOGITS
     Creature
    0.70
     qualities
    0.58
    çļ
    0.57
     proportions
    0.51
     rept
    0.50
     achievements
    0.49
     scholar
    0.49
     Achievement
    0.48
     achievement
    0.48
     quality
    0.48
    Activations Density 7.496%

    No Known Activations