© 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. 1635
    Prev
    Next
    INDEX
    Explanations

    timestamp formats in a specific format

    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
    127
    +0.14
    0.5%
    447
    +0.13
    0.4%
    62
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.04
    127
    +0.13
    0.03
    115
    +0.12
    0.03
    Negative Logits
    schild
    -1.01
    stood
    -0.91
    folios
    -0.91
    matic
    -0.89
    keyes
    -0.86
    DonaldTrump
    -0.85
    bread
    -0.84
    cube
    -0.83
    keye
    -0.83
    cells
    -0.82
    POSITIVE LOGITS
    01
    1.08
    ounce
    1.05
    28
    1.05
    å¹
    1.02
    04
    1.02
    08
    1.00
    21
    0.99
    17
    0.98
    18
    0.97
    30
    0.96
    Activations Density 0.252%

    No Known Activations