© 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. 2-RES-JB
    11. 13018
    Prev
    Next
    INDEX
    Explanations

    instances where someone is urging or requesting reconsideration or reevaluation of a decision or situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reconsideration and critical evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ring
    -0.69
    á
    -0.66
    opter
    -0.64
    bearing
    -0.63
    OTT
    -0.62
    ramid
    -0.59
    tale
    -0.58
    ART
    -0.58
     Kinnikuman
    -0.58
    oiler
    -0.58
    POSITIVE LOGITS
     reconsider
    1.23
     rethink
    1.16
     recons
    1.01
    itized
    0.89
    ĸļ
    0.85
    itiz
    0.78
     hesitation
    0.74
     revis
    0.73
     reinvest
    0.73
    ation
    0.72
    Activations Density 0.008%

    No Known Activations