© 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. 10951
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terms

    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
    •Layer 6 UMAP region: Mostly-local line at bottom - e2e-recon

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    326
    +0.08
    0.7%
    195
    +0.06
    0.5%
    339
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.08
    -0.06
    157
    +0.06
    0.14
    470
    +0.06
    0.09
    Negative Logits
    )."
    -0.55
    .).
    -0.54
    ]."
    -0.52
    }.
    -0.48
    .</
    -0.47
    })
    -0.43
    )).
    -0.42
    ).
    -0.42
    ?).
    -0.42
     });
    -0.42
    POSITIVE LOGITS
     Edit
    0.36
     partName
    0.35
     meanwhile
    0.35
     FANTASY
    0.32
    ¶
    0.32
    undrum
    0.32
    ibliography
    0.31
     Salmon
    0.31
    odore
    0.31
     Yak
    0.31
    Activations Density 6.634%

    No Known Activations