© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2098
    Prev
    Next
    INDEX
    Explanations

    terms related to actions or events happening in a sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of certain actions or occurrences related to activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aten
    -0.61
    opter
    -0.61
     notwithstanding
    -0.58
    amen
    -0.55
    click
    -0.54
     otherwise
    -0.53
     honestly
    -0.53
    until
    -0.53
     Ki
    -0.52
    just
    -0.52
    POSITIVE LOGITS
    ered
    0.68
    interstitial
    0.66
    agonists
    0.65
    ãĤ©
    0.65
    urb
    0.64
    ogged
    0.64
     anecd
    0.63
    }:
    0.63
    *:
    0.63
    ebted
    0.63
    Activations Density 0.460%

    No Known Activations