© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7740
    Prev
    Next
    INDEX
    Explanations

    phrases related to job titles or positions, specifically focusing on "assistant" roles

    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
    167
    +0.18
    0.7%
    101
    +0.17
    0.6%
    288
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.18
    0.06
    136
    +0.17
    0.05
    288
    +0.16
    0.06
    Negative Logits
    stakes
    -1.05
    =-=-=-=-=-=-=-=-
    -0.96
    ALE
    -0.96
    atche
    -0.95
    agra
    -0.94
    igation
    -0.91
    Ö¼
    -0.89
    ktop
    -0.89
    ERO
    -0.86
    bp
    -0.85
    POSITIVE LOGITS
     professor
    1.08
     assistant
    1.00
     adjunct
    0.90
     referees
    0.89
    iliary
    0.88
     Wend
    0.86
     Dean
    0.86
    ibles
    0.85
     lineman
    0.85
     assistants
    0.84
    Activations Density 0.775%

    No Known Activations