© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3454
    Prev
    Next
    INDEX
    Explanations

    references to failures or shortcomings

    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
    624
    +0.13
    0.5%
    91
    +0.13
    0.5%
    195
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.11
    195
    +0.13
    0.04
    247
    +0.13
    0.06
    Negative Logits
    odium
    -1.03
    verbs
    -0.98
    avis
    -0.94
    agog
    -0.92
    ieri
    -0.89
    arbon
    -0.88
    icles
    -0.88
    utra
    -0.86
    estamp
    -0.86
    ergy
    -0.85
    POSITIVE LOGITS
    istence
    1.03
     attitude
    0.97
     thereof
    0.93
     rate
    0.92
    FUL
    0.90
     fatigue
    0.88
    externalActionCode
    0.86
     unwillingness
    0.85
     mindset
    0.84
     guiActiveUn
    0.84
    Activations Density 1.323%

    No Known Activations