© 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. 7230
    Prev
    Next
    INDEX
    Explanations

    chemical and medical terms and information such as drug names and treatments

    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
    659
    +0.20
    0.6%
    102
    +0.18
    0.6%
    746
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.09
    67
    +0.18
    0.08
    588
    +0.17
    0.07
    Negative Logits
     GOODMAN
    -1.16
    ãĥĹ
    -1.02
    zai
    -1.01
    ĪĴ
    -0.99
    é¾įå
    -0.98
    HCR
    -0.97
    ileaks
    -0.94
     partName
    -0.93
    */(
    -0.93
     Blaster
    -0.89
    POSITIVE LOGITS
    ologne
    1.78
    rosso
    1.60
    ursor
    1.57
    ursed
    1.51
    ourses
    1.50
    inct
    1.49
    oding
    1.48
    uda
    1.45
    rawl
    1.43
    amps
    1.43
    Activations Density 1.316%

    No Known Activations