© 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. 3-RES-JB
    11. 11312
    Prev
    Next
    INDEX
    Explanations

    occurrences related to halting progress or events, including mentions of stalled plans or activities, and discussion of preventing or terminating actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to termination or failure, particularly in contexts like abortion or stalled processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SAY
    -0.77
    arning
    -0.76
    tymology
    -0.76
    renches
    -0.74
    anguage
    -0.74
    ©¶æ
    -0.74
    ansk
    -0.71
    asury
    -0.68
    cipl
    -0.67
    aws
    -0.67
    POSITIVE LOGITS
     abort
    1.24
     aborted
    0.94
    heimer
    0.77
     succeeding
    0.76
    ivals
    0.75
     botched
    0.73
     takeoff
    0.71
    IBLE
    0.71
     fetus
    0.68
     Zap
    0.66
    Activations Density 0.010%

    No Known Activations