© 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. 7-RES-JB
    11. 21190
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or groups providing financial support or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to donors, especially in the context of financial support or funding

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.78
    aeper
    -0.78
     Adventures
    -0.77
     Lob
    -0.70
    uku
    -0.66
     Bulls
    -0.65
    PASS
    -0.63
     Modes
    -0.63
     Bav
    -0.63
     Lamp
    -0.62
    POSITIVE LOGITS
    gee
    0.90
    hetical
    0.86
     laureate
    0.85
    hip
    0.85
    ervatives
    0.84
    hips
    0.81
    ervative
    0.81
    berus
    0.79
     donors
    0.78
     beware
    0.76
    Activations Density 0.034%

    No Known Activations