© 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 EvalsExportsinterp-engineNEWAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10943
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and testimony

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    326
    +0.15
    0.6%
    128
    +0.14
    0.5%
    556
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.15
    0.05
    128
    +0.14
    0.06
    659
    +0.14
    0.06
    Negative Logits
    ramid
    -1.06
    ãĥ¯ãĥ³
    -1.03
    ãĥ¼ãĤ¯
    -1.02
    BLIC
    -1.01
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.97
    éĹĺ
    -0.96
    ãĤ®
    -0.89
    ãĥį
    -0.88
    ilitarian
    -0.88
    姫
    -0.88
    POSITIVE LOGITS
    ugs
    1.46
    ips
    1.41
    idd
    1.41
    ipp
    1.41
    adders
    1.39
    ashes
    1.39
    ibr
    1.39
    oping
    1.38
    amin
    1.36
    agging
    1.34
    Activations Density 0.898%

    No Known Activations