© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 33704
    Prev
    Next
    INDEX
    Explanations

    diverse forms of the word 'funny'

    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
    +0.21
    1.0%
    267
    +0.13
    0.6%
    151
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.21
    0.13
    423
    +0.13
    0.08
    326
    +0.12
    0.14
    Negative Logits
    ainer
    -0.97
    ignt
    -0.81
    apers
    -0.78
    enfranch
    -0.77
    eded
    -0.77
    hent
    -0.77
    ignty
    -0.75
    ajor
    -0.74
    ership
    -0.73
    ports
    -0.72
    POSITIVE LOGITS
    netflix
    0.88
     GIF
    0.86
    ness
    0.81
     tale
    0.79
     funny
    0.78
     bone
    0.77
     Guys
    0.75
     anecdotes
    0.74
    glers
    0.74
    balls
    0.74
    Activations Density 3.904%

    No Known Activations