© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3525
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs or expenses

    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
    570
    +0.15
    0.5%
    328
    +0.12
    0.4%
    386
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.15
    0.05
    730
    +0.12
    0.05
    32
    +0.12
    0.05
    Negative Logits
     Seeking
    -0.92
    ullivan
    -0.91
    nai
    -0.91
    Else
    -0.85
    aucas
    -0.83
    vironment
    -0.83
    mbuds
    -0.82
    è¦ļéĨĴ
    -0.81
     Scrib
    -0.80
     Typ
    -0.78
    POSITIVE LOGITS
    umed
    1.17
     taxpayers
    1.07
    umers
    1.06
     prohib
    0.98
     premiums
    0.97
    payers
    0.96
     $
    0.96
    staking
    0.96
    liest
    0.95
     him
    0.95
    Activations Density 0.645%

    No Known Activations