Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 20980
    Prev
    Next
    INDEX
    Explanations

    words related to uploading files or content to a platform

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the action of uploading content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acist
    -0.76
    neg
    -0.71
    pha
    -0.70
    acha
    -0.68
     Hein
    -0.66
    orum
    -0.64
    oeuv
    -0.64
    lda
    -0.64
    endez
    -0.63
    plom
    -0.63
    POSITIVE LOGITS
    uploads
    0.94
     Upload
    0.94
    Upload
    0.88
     upload
    0.88
    upload
    0.82
     uploaded
    0.81
     Thumbnails
    0.80
    files
    0.73
    ster
    0.72
    lishing
    0.71
    Activations Density 0.015%

    No Known Activations