© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    Spanish words and terms related to espionage and national security

    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
    527
    +0.10
    0.5%
    88
    +0.10
    0.5%
    685
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.21
    288
    +0.10
    0.23
    659
    +0.09
    0.10
    Negative Logits
    folk
    -0.90
    ocalyptic
    -0.86
    Reviewer
    -0.83
    NetMessage
    -0.81
    essee
    -0.75
    IFIED
    -0.71
    ologically
    -0.71
    creen
    -0.70
    TPPStreamerBot
    -0.69
    cho
    -0.64
    POSITIVE LOGITS
     Esp
    0.83
    resso
    0.80
    ionage
    0.75
     Wilde
    0.64
    ably
    0.59
    icz
    0.59
     Connection
    0.57
    lished
    0.57
     Breaker
    0.57
    ira
    0.57
    Activations Density 6.419%

    No Known Activations