© 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. 1111
    Prev
    Next
    INDEX
    Explanations

    phrases relating to various forms of stopping or failure

    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
    488
    +0.07
    0.5%
    545
    +0.07
    0.5%
    532
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.07
    0.02
    750
    +0.07
    0.02
    238
    +0.07
    0.03
    Negative Logits
    adier
    -0.55
    -+-+
    -0.54
    fixes
    -0.47
    =-=-=-=-
    -0.45
    èĢħ
    -0.44
    Tags
    -0.42
    fell
    -0.41
     Schultz
    -0.40
    Ts
    -0.39
    WAR
    -0.39
    POSITIVE LOGITS
     carbs
    0.40
    ither
    0.40
    tenance
    0.39
     Ples
    0.39
    essential
    0.39
    pell
    0.38
    teness
    0.38
    marg
    0.38
     pursu
    0.38
     surplus
    0.37
    Activations Density 0.138%

    No Known Activations