© 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. 23576
    Prev
    Next
    INDEX
    Explanations

    information about different companies and organizations

    oai_token-act-pair · gpt-3.5-turbo

    leading companies or organizations in specific industries

    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
    ppings
    -0.85
     coughing
    -0.78
    oshenko
    -0.72
     nausea
    -0.71
    finger
    -0.71
    omach
    -0.70
     stump
    -0.69
     Koran
    -0.68
    etter
    -0.67
     anyway
    -0.67
    POSITIVE LOGITS
     headquartered
    1.21
     subsidiaries
    1.12
    ablished
    1.12
     Located
    1.08
    quartered
    1.02
     affiliates
    1.02
     founded
    1.00
     501
    0.97
     affiliated
    0.97
     founding
    0.97
    Activations Density 0.672%

    No Known Activations