© 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. 294
    Prev
    Next
    INDEX
    Explanations

    numerical ratings and scores related to various topics or entities

    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
    274
    +0.21
    0.7%
    195
    +0.19
    0.6%
    447
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.21
    0.04
    326
    +0.19
    0.04
    540
    +0.16
    0.05
    Negative Logits
    adr
    -1.22
    uve
    -1.12
     Alz
    -1.06
    orial
    -1.04
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -1.04
    vey
    -1.01
     Paleo
    -0.99
    dayName
    -0.98
    ansson
    -0.98
    ices
    -0.97
    POSITIVE LOGITS
     ratings
    1.60
     rating
    1.48
     Ratings
    1.32
     Rating
    1.18
    âĺħâĺħ
    1.15
    Rating
    1.08
     downgrade
    1.05
     rated
    1.04
    âĺħ
    1.03
    Beer
    1.02
    Activations Density 0.614%

    No Known Activations