© 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. 2855
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific event or concept called "Kick"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Kick" 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
    oric
    -0.76
     lapse
    -0.75
    imens
    -0.73
     excess
    -0.71
     Siber
    -0.68
     cler
    -0.67
     vest
    -0.66
    rig
    -0.66
    erie
    -0.64
     Oliv
    -0.63
    POSITIVE LOGITS
     Kick
    3.78
    Kick
    2.56
    kick
    2.04
     Knock
    1.19
     Kickstarter
    1.16
     Punch
    1.12
     KS
    1.08
     kick
    1.07
     Slash
    1.07
     kickoff
    1.00
    Activations Density 0.019%

    No Known Activations