© 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 Local
    9. 6-RES_SCL-AJT
    11. 35697
    Prev
    Next
    INDEX
    Explanations

    phrases related to petitions and campaigns

    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
    •Layer 6 UMAP region: Mixed in middle - local

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    1.3%
    526
    +0.11
    0.6%
    644
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.24
    0.12
    217
    +0.11
    0.06
    78
    +0.10
    0.06
    Negative Logits
    lasses
    -0.64
    ectar
    -0.58
     Afric
    -0.56
    çīĪ
    -0.53
    íķ
    -0.53
    rost
    -0.51
    winter
    -0.50
    orf
    -0.50
    antle
    -0.50
    mson
    -0.50
    POSITIVE LOGITS
     petitions
    0.73
     petition
    0.73
    naires
    0.71
    ingly
    0.70
    ers
    0.65
    aires
    0.62
    irection
    0.62
    ingham
    0.60
     filed
    0.60
     signatures
    0.60
    Activations Density 8.853%

    No Known Activations