© 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. 20266
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries ending with a question mark

    oai_token-act-pair · gpt-3.5-turbo

    questions, particularly rhetorical or exclamatory ones

    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
     practition
    -0.79
    avorite
    -0.78
     srf
    -0.78
    uckland
    -0.75
     carbohyd
    -0.74
     corrid
    -0.73
     satell
    -0.72
    ailability
    -0.71
     antidepress
    -0.70
    rament
    -0.70
    POSITIVE LOGITS
     Nope
    1.46
     Answer
    1.45
     Surely
    1.41
     Wouldn
    1.38
     Isn
    1.38
     Well
    1.33
     Why
    1.31
    Answer
    1.26
     Because
    1.25
     Didn
    1.25
    Activations Density 0.101%

    No Known Activations