© 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. 46037
    Prev
    Next
    INDEX
    Explanations

    references to violent acts or events, particularly those involving decapitation or execution

    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
    +0.16
    0.8%
    685
    +0.11
    0.5%
    553
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.16
    0.09
    639
    +0.11
    0.10
    553
    +0.10
    0.07
    Negative Logits
    soType
    -0.73
     explan
    -0.71
    rium
    -0.69
    ZX
    -0.69
    CRE
    -0.65
    BuyableInstoreAndOnline
    -0.64
     easing
    -0.62
    paren
    -0.62
    Depth
    -0.61
    Import
    -0.61
    POSITIVE LOGITS
     spree
    0.87
     corpses
    0.83
     murdered
    0.83
     murderers
    0.81
     murder
    0.81
    nikov
    0.80
     murders
    0.76
     murderer
    0.75
     death
    0.75
     victims
    0.75
    Activations Density 11.313%

    No Known Activations