© 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. 8-RES-JB
    11. 3088
    Prev
    Next
    INDEX
    Explanations

    names related to sports, specifically the name "Erik" with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    the presence of names associated with hockey players or figures in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĦ
    -0.73
    pher
    -0.69
    matically
    -0.65
    creen
    -0.64
    phis
    -0.64
     lig
    -0.63
    tons
    -0.62
    ODUCT
    -0.61
    arella
    -0.61
    frey
    -0.61
    POSITIVE LOGITS
     Wem
    1.00
     Spo
    0.90
    ansson
    0.87
     Hels
    0.81
    ulic
    0.81
     Alm
    0.81
     Larson
    0.81
    iewicz
    0.81
    kson
    0.80
    onen
    0.78
    Activations Density 0.069%

    No Known Activations