© 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. 0-RES-JB
    11. 2865
    Prev
    Next
    INDEX
    Explanations

    phrases related to hitting or striking something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hits" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verning
    -0.72
     consent
    -0.71
    ether
    -0.66
     clothed
    -0.65
     constituted
    -0.65
    AppData
    -0.64
    inus
    -0.61
     concealed
    -0.61
    PT
    -0.60
    astern
    -0.60
    POSITIVE LOGITS
     hits
    3.66
     Hits
    2.71
     hit
    2.33
    hit
    1.74
     hitting
    1.73
     slams
    1.60
     strikes
    1.60
     Hit
    1.57
     blows
    1.53
     misses
    1.53
    Activations Density 0.009%

    No Known Activations