© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 31413
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and financial matters

    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
    459
    +0.12
    0.6%
    16
    +0.11
    0.5%
    283
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.12
    0.03
    556
    +0.11
    0.05
    593
    +0.11
    0.04
    Negative Logits
     4090
    -0.72
    hang
    -0.69
    oteric
    -0.66
    SPONSORED
    -0.65
    ··
    -0.64
    OTOS
    -0.64
     Stras
    -0.64
     Luthor
    -0.61
     Pharma
    -0.61
    gerald
    -0.61
    POSITIVE LOGITS
    uced
    1.38
    ucing
    1.18
    uces
    1.17
    eem
    1.16
    ding
    1.15
    irect
    1.12
    uctor
    1.09
    uce
    1.08
    acted
    1.06
    uction
    1.05
    Activations Density 4.832%

    No Known Activations