© 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. 19951
    Prev
    Next
    INDEX
    Explanations

    the word "oh" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    the word "oh" and its variations, indicating expressions of realization or emotional responses

    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
     thousands
    -0.63
     flight
    -0.61
     private
    -0.61
     debris
    -0.61
     Staples
    -0.60
     CAS
    -0.60
     residue
    -0.60
     competitor
    -0.60
     nightly
    -0.60
     print
    -0.59
    POSITIVE LOGITS
    oh
    4.10
    OH
    1.90
    oha
    1.73
    Oh
    1.58
    ohl
    1.48
    ah
    1.46
    uh
    1.46
    oho
    1.43
    ok
    1.41
     oh
    1.38
    Activations Density 0.011%

    No Known Activations