© 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. 8-RES-JB
    11. 1098
    Prev
    Next
    INDEX
    Explanations

    sections of a website or newsletter, potentially related to notifications or summaries

    oai_token-act-pair · gpt-3.5-turbo

    content related to additional information and updates about various topics

    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
    venth
    -0.67
    etheless
    -0.64
    verend
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    illus
    -0.62
    iour
    -0.62
    minster
    -0.60
    ÅĤ
    -0.60
    efe
    -0.59
     tert
    -0.58
    POSITIVE LOGITS
     please
    1.10
    please
    0.98
     visit
    0.98
     click
    0.88
     CLICK
    0.85
     subscribe
    0.80
     including
    0.74
     Visit
    0.73
     consult
    0.72
    Visit
    0.71
    Activations Density 0.135%

    No Known Activations