© 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. 9-RES-JB
    11. 16345
    Prev
    Next
    INDEX
    Explanations

    capitalized names of organizations

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hitch
    -0.86
     flowering
    -0.85
     bloom
    -0.85
     jog
    -0.84
     yield
    -0.82
     haunt
    -0.78
     weave
    -0.74
     fade
    -0.72
     wid
    -0.71
     colon
    -0.71
    POSITIVE LOGITS
    ï¸ı
    1.14
    CEO
    1.10
    76561
    1.05
    HQ
    1.03
    STD
    1.03
    BUS
    0.98
    SHIP
    0.97
    uthor
    0.94
    TED
    0.94
    VICE
    0.92
    Activations Density 0.187%

    No Known Activations