© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 841
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal custody, care, and oversight

    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
    288
    +0.13
    0.5%
    285
    +0.13
    0.4%
    35
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.13
    0.04
    288
    +0.13
    0.04
    575
    +0.12
    0.04
    Negative Logits
    onite
    -1.09
    ãĥĥãĥī
    -1.00
    kered
    -0.99
    akedown
    -0.96
    BIP
    -0.84
    âĸ¬
    -0.82
    Publisher
    -0.81
    ãĥ³ãĤ¸
    -0.81
    enty
    -0.80
    UE
    -0.80
    POSITIVE LOGITS
    taker
    1.92
    giving
    1.64
    lessly
    1.52
    lessness
    1.36
    tta
    1.35
    taking
    1.32
    fully
    1.23
    ening
    1.21
    lington
    1.17
    maid
    1.16
    Activations Density 0.417%

    No Known Activations