© 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. 16899
    Prev
    Next
    INDEX
    Explanations

    names of editors or editorial positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different editorial roles and titles

    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
     perimeter
    -0.68
     plan
    -0.68
    rals
    -0.68
     sham
    -0.66
     carn
    -0.62
     nearby
    -0.62
     movements
    -0.61
     reun
    -0.61
     combine
    -0.61
    otte
    -0.61
    POSITIVE LOGITS
     Editor
    3.82
     Editors
    2.38
    Editor
    2.25
     editor
    1.98
    editor
    1.78
     Publisher
    1.67
     Editorial
    1.64
     Editing
    1.53
     Reporter
    1.49
     editors
    1.47
    Activations Density 0.011%

    No Known Activations