© 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. 12187
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a current state of availability or availability changes

    oai_token-act-pair · gpt-3.5-turbo

    statements about the availability or status of items or events

    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
    isms
    -0.68
     defeats
    -0.67
     stereotype
    -0.66
     extremes
    -0.66
     stroke
    -0.64
     contrasts
    -0.62
    soever
    -0.62
     caricature
    -0.61
    efficiency
    -0.60
     misuse
    -0.60
    POSITIVE LOGITS
     now
    1.19
     still
    1.14
     underway
    1.11
     slated
    1.05
     nearing
    1.04
     finally
    1.03
     NOW
    1.00
     currently
    1.00
    now
    0.96
     awaiting
    0.95
    Activations Density 0.416%

    No Known Activations