© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24448
    Prev
    Next
    INDEX
    Explanations

    keywords related to technical documents

    oai_token-act-pair · gpt-3.5-turbo

    bullet points or list items denoted by special characters or symbols

    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
    acia
    -0.86
    enos
    -0.86
    inki
    -0.84
    ividual
    -0.84
    ensibly
    -0.84
    abee
    -0.82
    estate
    -0.79
    nesday
    -0.77
    ional
    -0.76
    ione
    -0.76
    POSITIVE LOGITS
    âĢ¢âĢ¢âĢ¢âĢ¢
    1.66
    âĢ¢âĢ¢
    1.45
    ··
    0.97
     Own
    0.72
     Cart
    0.69
     Chiefs
    0.67
     |--
    0.65
     Written
    0.64
     Facilities
    0.64
     Tags
    0.64
    Activations Density 0.012%

    No Known Activations