© 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. 15234
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conflicts or disruptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "broke," particularly in contexts related to conflicts or significant events

    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
    alogy
    -0.66
    erva
    -0.65
    ulp
    -0.64
    etheless
    -0.64
    idency
    -0.63
    essee
    -0.61
    onz
    -0.61
    metics
    -0.60
    anto
    -0.60
    oran
    -0.60
    POSITIVE LOGITS
    neck
    0.92
     broke
    0.89
    breaks
    0.87
    owship
    0.80
    red
    0.78
    break
    0.77
    LEASE
    0.77
     break
    0.77
     breaks
    0.76
    breakers
    0.74
    Activations Density 0.014%

    No Known Activations