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. 8-RES-JB
    6. 2847
    Prev
    Next
    INDEX
    Explanations

    links to download PDF versions or books

    oai_token-act-pair · gpt-3.5-turbo

    elements related to downloadable content or file formats

    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
     Ragnarok
    -0.74
     revenge
    -0.71
    opoulos
    -0.71
     Carnage
    -0.64
     Galile
    -0.62
    spawn
    -0.62
    venge
    -0.58
    ythm
    -0.58
     bounty
    -0.57
     sweets
    -0.57
    POSITIVE LOGITS
    PDF
    1.14
     PDF
    1.13
    pdf
    1.08
     pdf
    1.05
     eBook
    0.95
    doi
    0.90
     Kindle
    0.86
     paperback
    0.84
     ISBN
    0.82
     Downloads
    0.80
    Activations Density 0.246%

    No Known Activations