© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16663
    Prev
    Next
    INDEX
    Explanations

    mentions of transportation accidents, specifically crashes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crash" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.75
    tern
    -0.73
    icrobial
    -0.71
    flu
    -0.69
    rov
    -0.69
    rolog
    -0.65
    resso
    -0.65
    cil
    -0.63
    itia
    -0.63
    ILA
    -0.62
    POSITIVE LOGITS
    worthiness
    1.14
    course
    0.90
     Course
    0.88
     landing
    0.81
     Landing
    0.74
     wreck
    0.73
     crash
    0.73
     crashes
    0.73
     Dive
    0.71
     helmet
    0.71
    Activations Density 0.045%

    No Known Activations