© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5038
    Prev
    Next
    INDEX
    Explanations

    mentions of sports related to golf and skiing

    oai_token-act-pair · gpt-3.5-turbo

    words related to sports activities and participants

    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
    entry
    -0.77
    ories
    -0.71
    tera
    -0.67
    insula
    -0.67
    rolet
    -0.67
    berra
    -0.66
    ente
    -0.65
    urable
    -0.65
    ensable
    -0.64
    ween
    -0.63
    POSITIVE LOGITS
     extraord
    0.94
    esses
    0.75
     Gael
    0.70
     who
    0.69
    digy
    0.68
     Sonny
    0.68
     laureate
    0.68
    culosis
    0.67
     derby
    0.67
     Sammy
    0.67
    Activations Density 0.091%

    No Known Activations