© 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. 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. 3009
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings or court activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to emotional development and media content

    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
    ks
    -0.78
    lahoma
    -0.77
    zig
    -0.74
    utor
    -0.73
    ichita
    -0.71
    rology
    -0.71
    ãĥĥ
    -0.71
    sect
    -0.70
    bd
    -0.69
    utch
    -0.69
    POSITIVE LOGITS
    ING
    1.56
    LY
    1.53
    MENT
    1.52
     OF
    1.47
    OUS
    1.46
    IES
    1.46
    INGS
    1.42
    ED
    1.41
    ABLE
    1.40
    BOOK
    1.39
    Activations Density 0.205%

    No Known Activations