© 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. 40681
    Prev
    Next
    INDEX
    Explanations

    names of characters and terms related to a specific fictional universe or series

    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
    537
    +0.11
    0.5%
    252
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.25
    393
    +0.10
    0.22
    160
    +0.10
    0.18
    Negative Logits
    ufact
    -0.77
    ieri
    -0.70
     msec
    -0.70
    rawdownloadcloneembedreportprint
    -0.66
    ngth
    -0.66
    ãĤ¡
    -0.65
     Lauder
    -0.65
    ãĥ£
    -0.65
    mingham
    -0.65
     Cla
    -0.64
    POSITIVE LOGITS
    tra
    0.86
    shaped
    0.86
    rays
    0.84
    coord
    0.83
    meter
    0.82
    axis
    0.82
    reme
    0.82
    series
    0.81
    Ray
    0.81
    linked
    0.80
    Activations Density 8.230%

    No Known Activations