© 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. 9874
    Prev
    Next
    INDEX
    Explanations

    phrases indicating importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significance or prominence

    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
    imilar
    -0.78
    izon
    -0.75
    olution
    -0.72
    aturated
    -0.69
    anners
    -0.69
    ikk
    -0.68
    bern
    -0.68
     Practices
    -0.68
    ividual
    -0.68
    ãĤ´
    -0.67
    POSITIVE LOGITS
     importantly
    1.29
     controvers
    1.03
     interestingly
    1.02
     cru
    1.00
     challeng
    0.96
     surprisingly
    0.95
     incidentally
    0.95
     fortunately
    0.94
     tragically
    0.93
     omin
    0.93
    Activations Density 0.122%

    No Known Activations