© 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 Local
    9. 6-RES_SCL-AJT
    11. 3794
    Prev
    Next
    INDEX
    Explanations

    phrases related to tax policy and tax reform

    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
    288
    +0.17
    0.7%
    447
    +0.13
    0.6%
    566
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.17
    0.07
    288
    +0.13
    0.12
    409
    +0.10
    0.05
    Negative Logits
    Ò
    -0.90
     Wond
    -0.79
     Wyn
    -0.77
     Ange
    -0.77
     Osw
    -0.76
     Hundred
    -0.76
     Jem
    -0.73
     Ukrain
    -0.73
     Despair
    -0.72
     Watts
    -0.71
    POSITIVE LOGITS
    payer
    1.34
    onomic
    1.28
    onomy
    1.26
    onom
    1.13
     collectors
    1.05
    payers
    1.04
    paying
    0.99
     collector
    0.95
     havens
    0.92
     avoidance
    0.90
    Activations Density 4.042%

    No Known Activations