Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20835
    Prev
    Next
    INDEX
    Explanations

    technical information and code snippets related to cards and functions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thy
    -0.73
     Juda
    -0.69
     advoc
    -0.69
     SOC
    -0.66
     dilig
    -0.65
     Monument
    -0.64
     Digest
    -0.60
     Tant
    -0.60
     Jou
    -0.60
     sacrific
    -0.59
    POSITIVE LOGITS
    braska
    0.77
    edia
    0.74
    iae
    0.70
    ghan
    0.69
    amacare
    0.69
    olean
    0.65
    generic
    0.64
    abyte
    0.64
    incoln
    0.62
    urers
    0.62
    Activations Density 0.330%

    No Known Activations