© 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. 11-RES-JB
    11. 3749
    Prev
    Next
    INDEX
    Explanations

    phrases related to highlighting or featuring something or someone

    oai_token-act-pair · gpt-3.5-turbo

    references to emerging or lesser-known artists and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achment
    -0.85
    inventoryQuantity
    -0.82
    Closure
    -0.78
    Downloadha
    -0.77
    ynthesis
    -0.76
    imester
    -0.74
    termination
    -0.74
    cription
    -0.73
    onz
    -0.73
    ebin
    -0.72
    POSITIVE LOGITS
     talented
    1.50
     artists
    1.44
     talents
    1.43
     talent
    1.34
     performers
    1.29
     personalities
    1.27
     celebrities
    1.23
     musicians
    1.21
     comedians
    1.20
     filmmakers
    1.16
    Activations Density 0.406%

    No Known Activations