Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 384
    Prev
    Next
    INDEX
    Explanations

    exclamations and interjections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief

    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
    abb
    -0.68
    orate
    -0.67
    copy
    -0.65
    edge
    -0.64
    ictions
    -0.64
    Central
    -0.61
    itations
    -0.61
    icip
    -0.60
    Hispanic
    -0.59
    atics
    -0.59
    POSITIVE LOGITS
     Oh
    3.31
     oh
    2.15
    Oh
    1.98
     Ah
    1.66
     Huh
    1.65
     Hey
    1.65
     Uh
    1.57
     Yeah
    1.49
     Wow
    1.46
     Okay
    1.44
    Activations Density 0.010%

    No Known Activations