© 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. 18673
    Prev
    Next
    INDEX
    Explanations

    single words with a special character associated with them

    oai_token-act-pair · gpt-3.5-turbo

    unique identifiers or symbols associated with specific topics or concepts

    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
     blacks
    -0.82
     Blacks
    -0.71
     creditors
    -0.67
     retirees
    -0.66
     miscar
    -0.65
     UD
    -0.64
     Arabs
    -0.64
     lots
    -0.64
     partners
    -0.64
     peanuts
    -0.63
    POSITIVE LOGITS
    framework
    1.02
    thing
    1.01
    formation
    1.00
    entity
    0.99
    issance
    0.98
    ï¸ı
    0.97
    expression
    0.97
    factor
    0.97
    ship
    0.96
    cation
    0.94
    Activations Density 0.233%

    No Known Activations