© 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. 14591
    Prev
    Next
    INDEX
    Explanations

    words related to names or specific terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and significant names related to people and places

    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
    ĨĴ
    -0.81
    hovah
    -0.74
    ©¶æ
    -0.74
    ciples
    -0.72
    rypted
    -0.70
    ł
    -0.69
    heon
    -0.68
    orea
    -0.68
    urrency
    -0.67
     nep
    -0.66
    POSITIVE LOGITS
    cloth
    0.87
    mand
    0.82
    zai
    0.80
    dress
    0.79
    hur
    0.79
    pring
    0.76
    pour
    0.76
    Downloadha
    0.75
    oust
    0.73
    enough
    0.72
    Activations Density 0.020%

    No Known Activations