© 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. 3-RES-JB
    11. 10758
    Prev
    Next
    INDEX
    Explanations

    mentions of spherical objects, specifically balls

    oai_token-act-pair · gpt-3.5-turbo

    references to spherical objects, particularly balls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.69
    MSN
    -0.67
    Eth
    -0.64
    yles
    -0.63
    EMBER
    -0.61
    rians
    -0.61
     guiIcon
    -0.60
     arts
    -0.60
    REM
    -0.60
    atalie
    -0.59
    POSITIVE LOGITS
    ball
    1.14
     balls
    1.12
    balls
    1.11
    wagen
    0.87
    buster
    0.85
     Balls
    0.83
    pell
    0.81
    halla
    0.80
    pun
    0.79
    hots
    0.79
    Activations Density 0.013%

    No Known Activations