© 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. 9-RES-JB
    11. 15386
    Prev
    Next
    INDEX
    Explanations

    plural words

    oai_token-act-pair · gpt-3.5-turbo

    plural possessive forms or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wise
    -0.63
     circumstances
    -0.60
     establishment
    -0.59
     seas
    -0.58
     Isis
    -0.56
     Labour
    -0.56
    TextColor
    -0.55
     Presbyterian
    -0.54
     serum
    -0.54
     prejudice
    -0.53
    POSITIVE LOGITS
    wana
    1.07
    ouls
    1.07
    ources
    1.06
    ubs
    1.01
    aturated
    0.99
    aurus
    0.98
    ucker
    0.97
    ervatives
    0.95
    nyder
    0.94
    uggest
    0.94
    Activations Density 0.250%

    No Known Activations