© 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. 34854
    Prev
    Next
    INDEX
    Explanations

    copyright-related phrases and legal terms

    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
    729
    +0.13
    0.5%
    288
    +0.12
    0.5%
    469
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.11
    253
    +0.12
    0.09
    36
    +0.11
    0.10
    Negative Logits
    externalActionCode
    -1.08
    Finish
    -0.81
    psc
    -0.81
    gran
    -0.81
    borough
    -0.76
    Gam
    -0.76
    utsu
    -0.75
    sonian
    -0.74
    kj
    -0.74
    grad
    -0.73
    POSITIVE LOGITS
     reserved
    1.13
     Reserved
    0.90
     trademarks
    0.83
     tradem
    0.79
     eas
    0.71
     pronouns
    0.70
    yrights
    0.69
     exclusively
    0.68
    istration
    0.67
     pronoun
    0.67
    Activations Density 6.494%

    No Known Activations