© 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. 1078
    Prev
    Next
    INDEX
    Explanations

    timestamps such as "o'clock"

    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
    232
    +0.07
    0.5%
    666
    +0.07
    0.5%
    220
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.07
    0.04
    387
    +0.07
    0.04
    666
    +0.06
    0.04
    Negative Logits
    NESS
    -0.58
    DERR
    -0.47
    imir
    -0.44
    LR
    -0.44
    âĸ¬
    -0.42
     packets
    -0.42
    GoldMagikarp
    -0.41
    theless
    -0.41
    ESH
    -0.41
     Territories
    -0.40
    POSITIVE LOGITS
    lymp
    0.54
    phthal
    0.54
    ugh
    0.53
    lder
    0.52
    omm
    0.52
    cean
    0.50
    ops
    0.50
    atmeal
    0.50
    ffic
    0.50
    mbuds
    0.50
    Activations Density 0.697%

    No Known Activations