© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17800
    Prev
    Next
    INDEX
    Explanations

    references to a specific "Brawl Bug Fix" and related modifications or discussions pertaining to it

    oai_token-act-pair · gpt-3.5-turbo

    references to brawls and associated injuries in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inent
    -0.81
    ebus
    -0.74
    inence
    -0.73
    oise
    -0.72
    ocy
    -0.71
    fires
    -0.71
    ote
    -0.68
    switch
    -0.67
    anyahu
    -0.66
    ologically
    -0.66
    POSITIVE LOGITS
    halla
    1.29
    é¾įåĸļ士
    1.23
    SourceFile
    0.88
    ashington
    0.80
    mson
    0.79
    MpServer
    0.79
    dayName
    0.79
    inventoryQuantity
    0.76
    hirt
    0.75
     Learns
    0.75
    Activations Density 0.035%

    No Known Activations