© 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 EvalsExportsAPI 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. 1007
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically last names but may include any kind of names

    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
    679
    +0.15
    0.7%
    343
    +0.14
    0.6%
    526
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.15
    0.06
    288
    +0.14
    0.08
    659
    +0.13
    0.05
    Negative Logits
    coni
    -0.70
    rower
    -0.68
     ejac
    -0.67
     ende
    -0.67
    kefeller
    -0.66
    berman
    -0.65
    opausal
    -0.65
     disproportionate
    -0.65
    iltration
    -0.64
    stros
    -0.63
    POSITIVE LOGITS
    atchewan
    1.43
    ansas
    1.06
    atoon
    1.05
     Rapids
    1.05
    edIn
    1.01
    aign
    0.97
    oln
    0.97
    ings
    0.89
    erness
    0.89
    erville
    0.89
    Activations Density 0.927%

    No Known Activations