© 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. 399
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming in languages such as Swift or Python

    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
    +0.20
    0.7%
    454
    +0.15
    0.5%
    750
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.20
    0.10
    176
    +0.15
    0.07
    289
    +0.14
    0.02
    Negative Logits
    hement
    -1.05
    ylum
    -0.98
    pmwiki
    -0.96
    undai
    -0.95
    Reviewer
    -0.94
    ktop
    -0.94
    lihood
    -0.86
    odore
    -0.86
     Laur
    -0.85
     Princ
    -0.83
    POSITIVE LOGITS
     decimal
    0.90
     ?
    0.87
     ();
    0.86
     }
    0.85
     ([
    0.82
    .$
    0.82
     ||
    0.81
     pipe
    0.81
    uple
    0.80
     (),
    0.78
    Activations Density 1.525%

    No Known Activations