© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 18502
    Prev
    Next
    INDEX
    Explanations

    phrases containing the abbreviation "DA" followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    references to the Development Authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    packing
    -0.80
    ties
    -0.77
    ments
    -0.77
    swick
    -0.75
    erous
    -0.71
    lining
    -0.71
    case
    -0.71
    rition
    -0.70
     Osw
    -0.70
    kies
    -0.69
    POSITIVE LOGITS
    ILY
    1.34
    VID
    1.14
    VIS
    0.93
    hyde
    0.93
    BLE
    0.89
    VE
    0.84
    ÄŁ
    0.81
    WN
    0.80
    pling
    0.80
    OTA
    0.80
    Activations Density 0.037%

    No Known Activations