© 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. 8566
    Prev
    Next
    INDEX
    Explanations

    quotes with varying emotions or impact

    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
    +0.14
    0.6%
    393
    +0.13
    0.5%
    467
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    108
    +0.14
    0.06
    426
    +0.13
    0.05
    627
    +0.12
    0.04
    Negative Logits
     pir
    -0.78
     laughing
    -0.76
     phon
    -0.76
     roundup
    -0.75
     disappro
    -0.74
     Scottish
    -0.72
     grammar
    -0.72
     scra
    -0.71
     Mayo
    -0.71
     polygamy
    -0.70
    POSITIVE LOGITS
    We
    1.20
    They
    1.19
    Because
    1.17
    Our
    1.16
    It
    1.15
    There
    1.13
    These
    1.10
    Otherwise
    1.08
    Demand
    1.08
    Clearly
    1.07
    Activations Density 0.098%

    No Known Activations