© 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. 7296
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or codes in the text

    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
    akening
    -0.87
    atism
    -0.84
    ĸļ
    -0.83
    ategory
    -0.81
    aken
    -0.74
    ItemTracker
    -0.73
    urrent
    -0.72
    raints
    -0.71
     Vaugh
    -0.71
    olics
    -0.70
    POSITIVE LOGITS
    00
    0.88
    LECT
    0.86
    rd
    0.82
    inately
    0.76
    aan
    0.74
    ¯¯¯¯
    0.74
    mm
    0.70
    backer
    0.69
    utenant
    0.68
     Shades
    0.68
    Activations Density 0.061%

    No Known Activations