© 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. 0-RES-JB
    11. 1256
    Prev
    Next
    INDEX
    Explanations

    instances of the word "pushing" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pushing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lear
    -0.71
    BN
    -0.70
    onym
    -0.67
    Registered
    -0.65
     Lot
    -0.64
    ocry
    -0.64
     Bachelor
    -0.63
    ith
    -0.62
     Book
    -0.62
    eret
    -0.61
    POSITIVE LOGITS
     pushing
    3.01
     pressuring
    1.93
     push
    1.84
     pushes
    1.78
     pulling
    1.77
     pushed
    1.75
    push
    1.72
     squeezing
    1.71
    Push
    1.62
     slamming
    1.59
    Activations Density 0.017%

    No Known Activations