© 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. 23995
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "breaker", with a particular focus on high activations for the term "deal-breaker"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to barriers or disruptions in various contexts

    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
    jriwal
    -0.75
    umerable
    -0.75
    icably
    -0.69
    itates
    -0.67
    anium
    -0.67
    elaide
    -0.66
    cium
    -0.65
    ives
    -0.65
    Ku
    -0.63
     ammon
    -0.63
    POSITIVE LOGITS
    breakers
    0.91
    breaker
    0.89
    é¾įå¥ij士
    0.72
    coni
    0.70
     breaker
    0.69
    hip
    0.67
    unker
    0.65
    女
    0.63
    etter
    0.63
     Gustav
    0.63
    Activations Density 0.040%

    No Known Activations