© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    references to files, directories, commands, and file operations

    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
    +0.20
    0.7%
    211
    +0.13
    0.5%
    285
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.20
    0.03
    653
    +0.13
    0.04
    531
    +0.12
    0.04
    Negative Logits
    osate
    -1.15
    anson
    -1.07
    ĵĺ
    -1.02
     Azerb
    -0.96
    apo
    -0.93
    ansen
    -0.93
    axter
    -0.93
    isol
    -0.92
     Bellev
    -0.92
    sylvania
    -0.92
    POSITIVE LOGITS
    ystem
    1.37
     descriptor
    1.30
    ettes
    1.22
    handle
    1.18
    Upload
    1.16
    ette
    1.16
    types
    1.10
     (.
    1.02
    thumbnails
    1.02
     descript
    1.02
    Activations Density 0.630%

    No Known Activations