© 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. 0-RES-JB
    11. 2382
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing the conclusion or outcome of events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conclusions or endings

    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
    itability
    -0.54
     sy
    -0.52
     fertile
    -0.51
     Pra
    -0.51
    pell
    -0.51
    erk
    -0.49
    HCR
    -0.49
    amina
    -0.49
     heartbeat
    -0.48
     Hicks
    -0.48
    POSITIVE LOGITS
     ended
    3.33
     Ended
    2.43
     ends
    2.09
     lasted
    1.74
     Ends
    1.68
     concluded
    1.68
     culminated
    1.63
     ending
    1.63
     end
    1.60
    ended
    1.56
    Activations Density 0.012%

    No Known Activations