© 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. 7-RES-JB
    11. 13491
    Prev
    Next
    INDEX
    Explanations

    words related to gaming controllers

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming controllers

    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
    ews
    -0.91
    olit
    -0.79
    iary
    -0.75
    onym
    -0.74
    gow
    -0.72
    ocaust
    -0.69
    entimes
    -0.69
     corpus
    -0.66
     Moonlight
    -0.66
    aciously
    -0.66
    POSITIVE LOGITS
     controller
    0.86
    pad
    0.82
    rollers
    0.81
     controllers
    0.77
    SHIP
    0.76
    controller
    0.73
    washer
    0.70
    Focus
    0.69
     Royale
    0.67
    wright
    0.67
    Activations Density 0.041%

    No Known Activations