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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 6683
    Prev
    Next
    INDEX
    Explanations

    mentions of governmental entities or structures, particularly federal and state levels

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly "and" or "or," indicating lists or connections between ideas

    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
    eks
    -0.69
    bos
    -0.66
    blocks
    -0.65
    ãĤ©
    -0.65
    ï¸
    -0.63
     rods
    -0.62
     Balls
    -0.61
     Bett
    -0.60
    aterasu
    -0.59
     Malk
    -0.59
    POSITIVE LOGITS
     allied
    0.90
    rogen
    0.90
    rogens
    0.88
    incial
    0.87
    heastern
    0.81
    gian
    0.79
    private
    0.79
     continental
    0.79
    GI
    0.79
     international
    0.78
    Activations Density 0.102%

    No Known Activations