© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 13613
    Prev
    Next
    INDEX
    Explanations

    points or scores related to different categories or items

    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
    447
    +0.15
    0.6%
    326
    +0.12
    0.4%
    432
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.15
    0.06
    238
    +0.12
    0.06
    326
    +0.12
    0.08
    Negative Logits
    hement
    -0.92
    ews
    -0.88
    Compan
    -0.86
    phia
    -0.81
    Plot
    -0.79
    Honest
    -0.78
    Buffer
    -0.77
    Untitled
    -0.76
    :/
    -0.74
    vic
    -0.73
    POSITIVE LOGITS
    imore
    1.01
    onga
    0.79
     Streaming
    0.75
     cir
    0.72
    "]=>
    0.72
     magnification
    0.69
     apiece
    0.68
     refuel
    0.68
     unlocked
    0.67
    ĵĺ
    0.66
    Activations Density 1.042%

    No Known Activations