© 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. 20374
    Prev
    Next
    INDEX
    Explanations

    pieces of information or updates in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the receipt of information or updates

    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
    dominated
    -0.68
    roying
    -0.66
    cffff
    -0.65
    ournament
    -0.65
    usterity
    -0.63
     offend
    -0.62
    Downloadha
    -0.62
     hated
    -0.61
    orship
    -0.61
    erenn
    -0.61
    POSITIVE LOGITS
     confirmation
    1.66
     clarification
    1.53
     information
    1.48
     details
    1.47
     evidence
    1.43
     indications
    1.42
     insight
    1.41
     hints
    1.41
     clues
    1.41
     answers
    1.40
    Activations Density 0.403%

    No Known Activations