© 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. 12866
    Prev
    Next
    INDEX
    Explanations

    exciting and emotionally driven content

    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
    608
    +0.12
    0.7%
    311
    +0.09
    0.5%
    653
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.20
    288
    +0.09
    0.20
    464
    +0.08
    0.08
    Negative Logits
    loo
    -0.64
    boarding
    -0.60
    ding
    -0.57
    hip
    -0.54
    dot
    -0.54
    fall
    -0.53
    living
    -0.52
     lightsaber
    -0.52
    lists
    -0.51
    tar
    -0.50
    POSITIVE LOGITS
    ruciating
    0.82
    itement
    0.82
    Exc
    0.68
    use
    0.67
    ixels
    0.66
    veyard
    0.66
    umph
    0.65
    andum
    0.62
    ursor
    0.62
    redible
    0.61
    Activations Density 6.749%

    No Known Activations