© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6865
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "esh" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.85
    ertodd
    -0.83
     carbohyd
    -0.80
    ļéĨĴ
    -0.69
    emort
    -0.68
    STER
    -0.67
    notation
    -0.66
    secut
    -0.66
    dylib
    -0.66
    */(
    -0.65
    POSITIVE LOGITS
    merga
    1.35
    adow
    1.14
    ould
    0.98
    esh
    0.96
    awar
    0.95
    awk
    0.95
    arma
    0.95
    ield
    0.93
    nikov
    0.93
    adows
    0.92
    Activations Density 0.006%

    No Known Activations