© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 21089
    Prev
    Next
    INDEX
    Explanations

    mentions of crashes or crash-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crash" related to accidents or failures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icrobial
    -0.71
    cil
    -0.68
    achu
    -0.68
    itia
    -0.65
    tern
    -0.65
    rolog
    -0.64
    åĮ
    -0.64
    ROR
    -0.63
    Ľ
    -0.62
    ITION
    -0.61
    POSITIVE LOGITS
    worthiness
    1.11
     Dive
    0.94
     crashes
    0.91
     crash
    0.85
    ulence
    0.77
     wreck
    0.77
    ulent
    0.75
     dumps
    0.74
    course
    0.73
     Course
    0.73
    Activations Density 0.029%

    No Known Activations