© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5349
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ability to do something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    490
    +0.19
    0.6%
    311
    +0.14
    0.5%
    665
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.19
    0.06
    665
    +0.14
    0.04
    311
    +0.13
    0.01
    Negative Logits
     Technique
    -0.91
    edient
    -0.90
     Tradition
    -0.88
     Bots
    -0.84
     Bounty
    -0.83
    flags
    -0.82
    machine
    -0.82
     Rising
    -0.81
    alien
    -0.81
    CPU
    -0.81
    POSITIVE LOGITS
    bodied
    1.29
    ioned
    1.25
    't
    1.20
    reys
    1.11
     access
    1.08
    awaru
    1.07
    iary
    1.05
    hing
    1.03
    ittees
    1.03
    rison
    1.03
    Activations Density 0.333%

    No Known Activations