© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39846
    Prev
    Next
    INDEX
    Explanations

    mentions of deadly events or situations

    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
    +0.19
    1.0%
    288
    +0.10
    0.5%
    290
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.19
    0.16
    195
    +0.10
    -0.01
    271
    +0.08
    0.04
    Negative Logits
    ourced
    -0.74
    ĸļ
    -0.69
    erous
    -0.68
    arity
    -0.67
    ļéĨĴ
    -0.67
    unda
    -0.66
     Username
    -0.65
    agate
    -0.65
     Libraries
    -0.64
    ership
    -0.63
    POSITIVE LOGITS
     poison
    0.79
     poisonous
    0.79
     lethal
    0.74
     wounding
    0.74
     dose
    0.73
     combination
    0.72
     weapons
    0.71
     toll
    0.71
     injection
    0.71
     assault
    0.70
    Activations Density 9.315%

    No Known Activations