© 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. 23251
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or organizations, especially related to historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or political entities

    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
    stood
    -0.73
    by
    -0.67
    gment
    -0.66
    bernatorial
    -0.65
    bys
    -0.65
    leground
    -0.62
    uality
    -0.61
    thood
    -0.57
     seiz
    -0.57
    oplan
    -0.57
    POSITIVE LOGITS
     themselves
    0.86
     during
    0.86
     beforehand
    0.79
     onto
    0.77
     towards
    0.74
     himself
    0.74
    iets
    0.74
     Himself
    0.73
     pursuant
    0.71
     into
    0.70
    Activations Density 0.472%

    No Known Activations