© 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. 8-RES-JB
    11. 1041
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to images or documents located below in a page

    oai_token-act-pair · gpt-3.5-turbo

    references to content or elements located beneath in a document or webpage

    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
    ãĥı
    -0.71
    士
    -0.69
    ãĥ³ãĤ¸
    -0.65
    ivities
    -0.64
    ãĤ¹ãĥĪ
    -0.64
    Writ
    -0.63
    в
    -0.62
    hya
    -0.62
    mails
    -0.62
    ument
    -0.61
    POSITIVE LOGITS
    ground
    0.96
    ebin
    0.79
     summar
    0.76
    imeo
    0.72
    :-
    0.69
     tradem
    0.68
     screenshot
    0.67
    eatures
    0.66
    essage
    0.66
    tics
    0.65
    Activations Density 0.033%

    No Known Activations