© 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. 7977
    Prev
    Next
    INDEX
    Explanations

    words related to quick and significant changes or turnarounds

    oai_token-act-pair · gpt-3.5-turbo

    themes related to turnaround and change

    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
    aband
    -0.73
    amm
    -0.70
    anting
    -0.68
    ricted
    -0.66
    occupied
    -0.65
    lect
    -0.64
     occupying
    -0.64
     residing
    -0.64
     emitted
    -0.64
    modules
    -0.64
    POSITIVE LOGITS
     turnaround
    3.80
     reversal
    1.35
     slowdown
    1.28
    oried
    1.00
     downturn
    0.99
     revers
    0.91
    ocene
    0.90
     redemption
    0.90
     comeback
    0.89
     renaissance
    0.88
    Activations Density 0.042%

    No Known Activations