© 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. 16968
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or data

    oai_token-act-pair · gpt-3.5-turbo

    commas in listings or enumerations

    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
    aky
    -0.61
    chuk
    -0.60
    iny
    -0.55
     Vaugh
    -0.54
    Override
    -0.53
     explan
    -0.51
    afer
    -0.51
    abl
    -0.50
    DN
    -0.50
    Bride
    -0.49
    POSITIVE LOGITS
     huh
    0.95
     etc
    0.87
     please
    0.78
     namely
    0.78
     including
    0.72
    govtrack
    0.71
     eh
    0.68
     plus
    0.68
     meanwhile
    0.67
     which
    0.66
    Activations Density 0.219%

    No Known Activations