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

    Neuronpedia

    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. 1-RES-JB
    11. 22539
    Prev
    Next
    INDEX
    Explanations

    names related to sports personalities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istic
    -0.81
    âĶĢâĶĢâĶĢâĶĢ
    -0.77
    archs
    -0.71
    Jews
    -0.70
    istically
    -0.69
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
     Drift
    -0.67
    astically
    -0.66
    obar
    -0.65
    uncle
    -0.65
    POSITIVE LOGITS
    hof
    1.01
    etz
    0.87
     Issa
    0.85
    sbm
    0.85
    yk
    0.82
    é¾
    0.81
    DEN
    0.78
    berry
    0.78
    gren
    0.77
    lder
    0.74
    Activations Density 0.029%

    No Known Activations