© 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. 4-RES-JB
    11. 14818
    Prev
    Next
    INDEX
    Explanations

    instances of the word "broken" with varying degrees of intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "broken" related to various contexts and conditions

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

    No Comments

    Negative Logits
    imental
    -0.83
    itatively
    -0.82
    azor
    -0.79
    minist
    -0.79
    urai
    -0.76
    orial
    -0.74
    icals
    -0.73
    idency
    -0.73
    erva
    -0.72
    rons
    -0.72
    POSITIVE LOGITS
    neck
    0.90
     broken
    0.81
    broken
    0.81
     bones
    0.80
    bones
    0.77
     Broken
    0.74
    edient
    0.72
     necks
    0.72
    hearted
    0.70
     broke
    0.68
    Activations Density 0.016%

    No Known Activations