© 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. 1-RES-JB
    11. 16826
    Prev
    Next
    INDEX
    Explanations

    terms related to blitzing in sports or metaphorically describing a rapid, overwhelming assault or action

    oai_token-act-pair · gpt-3.5-turbo

    the term "blitz" and its variations, indicating contexts related to aggressive or rapid actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akin
    -0.76
    inguishable
    -0.75
    aft
    -0.74
    uct
    -0.73
    Dialogue
    -0.71
    argo
    -0.67
    Parts
    -0.64
    REAM
    -0.64
     Founding
    -0.62
    avery
    -0.61
    POSITIVE LOGITS
     blitz
    1.36
     Blitz
    1.04
    rieg
    0.99
    ãĥĦ
    0.98
    schild
    0.95
    éĹĺ
    0.94
     absor
    0.86
    pread
    0.83
    heit
    0.81
    iflower
    0.80
    Activations Density 0.007%

    No Known Activations