© 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. 22527
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a forceful action or a significant effort

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "pull out"

    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
    ould
    -0.77
    llah
    -0.70
    esa
    -0.68
    orld
    -0.66
    umbered
    -0.66
    hedon
    -0.64
    eli
    -0.64
    pton
    -0.61
    enegger
    -0.60
    Queue
    -0.60
    POSITIVE LOGITS
    stretched
    0.83
    wards
    0.77
    itives
    0.72
     microphones
    0.72
     levers
    0.71
     roots
    0.67
    Snap
    0.64
     Medline
    0.63
     weeds
    0.63
     loopholes
    0.61
    Activations Density 0.035%

    No Known Activations