© 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. 10-RES-JB
    11. 9266
    Prev
    Next
    INDEX
    Explanations

    keywords related to data management and software development

    oai_token-act-pair · gpt-3.5-turbo

    references to data structures and data management concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wartime
    -0.68
    Ħ¢
    -0.65
     MacArthur
    -0.63
     sheer
    -0.63
     condem
    -0.63
     Cooke
    -0.62
     hars
    -0.62
     notoriously
    -0.62
     stren
    -0.62
    nesty
    -0.61
    POSITIVE LOGITS
    _
    0.94
    ().
    0.94
     node
    0.91
    Controller
    0.86
    Button
    0.84
     nodes
    0.84
    Items
    0.84
    Node
    0.84
    ()
    0.83
    Stats
    0.83
    Activations Density 0.431%

    No Known Activations