© 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. 1-RES-JB
    11. 16392
    Prev
    Next
    INDEX
    Explanations

    references to digital technology or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to digital technology and digital-related terms

    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
    PsyNetMessage
    -0.78
    enger
    -0.73
    ebin
    -0.73
    unct
    -0.72
    zzi
    -0.71
    utherford
    -0.70
    sburgh
    -0.69
    pell
    -0.69
    hov
    -0.67
    qt
    -0.66
    POSITIVE LOGITS
     Digital
    1.06
    olor
    1.00
    Digital
    0.94
    Ocean
    0.87
     Downloads
    0.82
     Collections
    0.77
    netic
    0.75
     Goods
    0.75
    digital
    0.74
     Graphic
    0.72
    Activations Density 0.006%

    No Known Activations