© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets and functions related to multithreading and asynchronous task handling

    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
    609
    +0.14
    0.5%
    196
    +0.14
    0.5%
    651
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.14
    0.03
    609
    +0.14
    0.03
    196
    +0.13
    0.03
    Negative Logits
    gaard
    -1.43
    yss
    -1.19
    endon
    -1.15
    ologies
    -1.12
    ILA
    -1.10
    omon
    -1.08
    OHN
    -1.07
    ingo
    -1.05
    ocrine
    -1.05
    pez
    -1.04
    POSITIVE LOGITS
     rc
    1.06
     tall
    1.05
    ptr
    1.01
     (*
    1.00
     stra
    0.88
     attm
    0.86
     wid
    0.85
    []
    0.84
     sum
    0.81
    acters
    0.81
    Activations Density 0.226%

    No Known Activations