© 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. 33376
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms with a numerical value in it

    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
    +0.18
    0.9%
    659
    +0.12
    0.6%
    128
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    742
    +0.18
    0.07
    154
    +0.12
    0.10
    137
    +0.10
    0.03
    Negative Logits
    éĹĺ
    -0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.72
    ãĤ®
    -0.69
    ãĥ¯ãĥ³
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.67
    OLOGY
    -0.67
    ãĥ¼ãĤ¯
    -0.66
    hower
    -0.61
    é¾įå¥ij士
    -0.59
     Primal
    -0.59
    POSITIVE LOGITS
    adders
    1.26
    ugs
    1.14
    ibr
    1.11
    ibrarian
    1.09
    idd
    1.09
    ipp
    1.09
    ashes
    1.07
    ips
    1.06
    agging
    1.05
    ongh
    1.03
    Activations Density 8.536%

    No Known Activations