© 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. 6-RES-JB
    11. 5626
    Prev
    Next
    INDEX
    Explanations

    names of professional athletes

    oai_token-act-pair · gpt-3.5-turbo

    names of players or athletes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pengu
    -0.79
     mathematic
    -0.77
     educators
    -0.73
     mathemat
    -0.72
    izoph
    -0.71
     simultane
    -0.70
    Issue
    -0.69
     horm
    -0.68
    Assembly
    -0.68
     philosophers
    -0.68
    POSITIVE LOGITS
     Jr
    1.19
     teammate
    0.95
    oglu
    0.92
     coached
    0.91
     III
    0.88
     Injury
    0.85
    ski
    0.83
     injury
    0.81
     vacated
    0.80
     Defensive
    0.80
    Activations Density 0.205%

    No Known Activations