© 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. 3163
    Prev
    Next
    INDEX
    Explanations

    verb forms related to directions or actions, such as "turn", "ended up", and "screaming" in a context suggesting tension or conflict

    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
    195
    +0.19
    0.6%
    113
    +0.13
    0.5%
    128
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    586
    +0.19
    0.05
    195
    +0.13
    0.03
    242
    +0.13
    0.05
    Negative Logits
    è¦ļéĨĴ
    -1.41
    ropolitan
    -1.21
    inately
    -1.01
    icipated
    -0.98
    capacity
    -0.97
    foundation
    -0.96
    mma
    -0.95
    ording
    -0.94
    bour
    -0.89
    agher
    -0.87
    POSITIVE LOGITS
    coat
    0.98
     into
    0.97
    ends
    0.96
    about
    0.95
     inward
    0.94
     awa
    0.93
    around
    0.93
     shif
    0.91
    rid
    0.89
     Turns
    0.85
    Activations Density 0.958%

    No Known Activations