© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9169
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific term or concept that is repeated frequently throughout passages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammad
    -0.77
     pend
    -0.72
    ¥µ
    -0.72
    theless
    -0.69
    etheus
    -0.64
    ordan
    -0.62
    velt
    -0.61
    zona
    -0.61
     Vaj
    -0.61
     Ground
    -0.59
    POSITIVE LOGITS
    terness
    1.18
    umen
    1.12
    buck
    1.03
    ches
    0.99
    meal
    0.96
    wig
    0.96
    umin
    0.93
    reet
    0.92
    chery
    0.89
    ching
    0.88
    Activations Density 0.021%

    No Known Activations