© 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. 4-RES-JB
    11. 7616
    Prev
    Next
    INDEX
    Explanations

    names and terms related to specific individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or organization related to governance or authority

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

    No Comments

    Negative Logits
    lain
    -0.94
    spin
    -0.86
    lier
    -0.83
    rooms
    -0.82
    size
    -0.81
    lined
    -0.78
    lot
    -0.75
    aign
    -0.75
    sw
    -0.74
    tons
    -0.74
    POSITIVE LOGITS
    Äĩ
    1.31
    ère
    1.04
    qi
    1.03
    oti
    1.00
    plom
    0.92
    ÃŁ
    0.91
    orno
    0.89
    udi
    0.88
    zzo
    0.87
    BILITY
    0.86
    Activations Density 0.048%

    No Known Activations