© 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. 0-RES-JB
    11. 1267
    Prev
    Next
    INDEX
    Explanations

    references to financial supporters or contributors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of donors and volunteers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OVA
    -0.66
    inc
    -0.61
     picture
    -0.61
    ime
    -0.58
    character
    -0.58
     thing
    -0.56
    man
    -0.56
     sack
    -0.56
     letter
    -0.56
    utation
    -0.56
    POSITIVE LOGITS
     attendees
    2.09
     donors
    2.08
     contributors
    2.02
     patrons
    1.96
     volunteers
    1.92
     backers
    1.90
     listeners
    1.86
     participants
    1.82
     drinkers
    1.80
     testers
    1.78
    Activations Density 0.063%

    No Known Activations