© 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. 6093
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    statements about the existence or presence of items or entities

    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
    é¾įå¥ij士
    -0.92
    imeters
    -0.71
    quickShipAvailable
    -0.70
    ogle
    -0.65
    appropriate
    -0.64
    irtual
    -0.63
    mate
    -0.63
    mental
    -0.62
    paren
    -0.58
    met
    -0.58
    POSITIVE LOGITS
     Fleet
    0.68
     sailed
    0.67
     salute
    0.67
     Norfolk
    0.65
     disbanded
    0.65
    urion
    0.64
    nor
    0.63
     fleet
    0.62
     Orn
    0.62
    umbai
    0.62
    Activations Density 0.705%

    No Known Activations