© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    expressions related to forceful impact or action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "hit" in various contexts

    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
    ouver
    -0.78
    pires
    -0.74
    ¥ŀ
    -0.73
     tyrann
    -0.69
     conve
    -0.68
    etheless
    -0.66
     horns
    -0.65
     offic
    -0.64
     displaying
    -0.63
    MpServer
    -0.63
    POSITIVE LOGITS
    hit
    1.16
    achi
    0.93
    oshi
    0.88
    endra
    0.83
    ãĥĥãĤ¯
    0.82
    chens
    0.79
    ched
    0.79
    hog
    0.78
    enson
    0.76
    ingly
    0.76
    Activations Density 0.011%

    No Known Activations