© 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. 32642
    Prev
    Next
    INDEX
    Explanations

    phrases related to critical analysis and commentary on cultural and societal issues

    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
    447
    +0.26
    1.2%
    393
    +0.11
    0.5%
    526
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.26
    0.38
    447
    +0.11
    0.40
    64
    +0.11
    -0.13
    Negative Logits
    SourceFile
    -0.65
    LOCK
    -0.64
    TPP
    -0.63
    ress
    -0.63
    INESS
    -0.63
    DragonMagazine
    -0.62
    anan
    -0.61
    ptives
    -0.61
    ACT
    -0.61
    amount
    -0.61
    POSITIVE LOGITS
     behalf
    1.27
    etime
    1.09
     occasion
    0.93
    eness
    0.90
    coming
    0.89
     steroids
    0.88
    screen
    0.88
    site
    0.87
    erous
    0.87
    sets
    0.86
    Activations Density 6.970%

    No Known Activations