© 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. 8-RES-JB
    11. 308
    Prev
    Next
    INDEX
    Explanations

    words related to research and investigation

    oai_token-act-pair · gpt-3.5-turbo

    word forms that contain "ear," indicating a focus on related terms

    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
    naires
    -0.70
     Strauss
    -0.64
    apo
    -0.63
    ère
    -0.62
     inconvenient
    -0.59
    ktop
    -0.58
     Gutierrez
    -0.57
    orb
    -0.57
     dots
    -0.57
     Bastard
    -0.56
    POSITIVE LOGITS
    nings
    1.24
    ning
    1.10
    lier
    1.06
    cies
    1.00
    ls
    0.93
    cy
    0.91
    gments
    0.90
    thing
    0.90
    ches
    0.90
    sworth
    0.90
    Activations Density 0.045%

    No Known Activations