© 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. 3993
    Prev
    Next
    INDEX
    Explanations

    common objects or concepts in a setting such as a workplace or social gathering

    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
    259
    +0.15
    0.6%
    181
    +0.12
    0.5%
    492
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.15
    0.20
    480
    +0.12
    -0.05
    181
    +0.12
    0.10
    Negative Logits
    \\\\\\\\
    -1.11
    ĸļ
    -0.96
    byss
    -0.95
     Bake
    -0.83
    ĪĴ
    -0.83
     Belg
    -0.81
    clus
    -0.81
     Beir
    -0.81
    Nob
    -0.76
    Tier
    -0.74
    POSITIVE LOGITS
     Continuous
    0.77
    owship
    0.75
     regrets
    0.71
     Peninsula
    0.71
     rpm
    0.70
     CFR
    0.70
     victimized
    0.68
     misunderstand
    0.68
     hooks
    0.67
     RPM
    0.67
    Activations Density 14.652%

    No Known Activations