© 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. 7-RES-JB
    6. 1544
    Prev
    Next
    INDEX
    Explanations

    numerical figures or punctuation marks used as separators between items

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics presented in a list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    othal
    -0.86
    udic
    -0.79
    aults
    -0.75
    erer
    -0.73
    aughter
    -0.72
    enthal
    -0.66
    uve
    -0.65
    ierre
    -0.64
    ERC
    -0.63
    istas
    -0.61
    POSITIVE LOGITS
    ··
    1.30
    ilities
    0.77
    âĢ¢âĢ¢
    0.75
    ¼
    0.73
    teen
    0.72
    ¾
    0.72
    lat
    0.70
    µ
    0.69
    te
    0.69
     Joined
    0.69
    Activations Density 0.027%

    No Known Activations