© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10144
    Prev
    Next
    INDEX
    Explanations

    keywords related to news alerts and humanitarian crises

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    377
    +0.15
    0.5%
    210
    +0.14
    0.4%
    192
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.04
    508
    +0.14
    0.03
    453
    +0.13
    0.02
    Negative Logits
    eon
    -1.07
    tick
    -1.05
    cling
    -1.01
    ard
    -0.97
    ittal
    -0.95
    âĸ¬
    -0.94
    iple
    -0.94
    orate
    -0.93
     Brach
    -0.93
    auri
    -0.92
    POSITIVE LOGITS
     humanitarian
    1.07
    ensibly
    0.99
     intervention
    0.96
     Refugee
    0.96
     intervene
    0.96
     ceasefire
    0.94
    faith
    0.91
     Aid
    0.89
     interven
    0.89
     amnesty
    0.88
    Activations Density 0.204%

    No Known Activations