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. 6-RES-JB
    6. 8373
    Prev
    Next
    INDEX
    Explanations

    references to a mythological beast or powerful entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "beast" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bered
    -0.89
    encing
    -0.75
    aded
    -0.69
    PsyNetMessage
    -0.68
     slee
    -0.68
    ixel
    -0.68
    arters
    -0.67
    ples
    -0.67
    UTION
    -0.66
    licted
    -0.64
    POSITIVE LOGITS
     Incarn
    0.86
    gey
    0.86
    ous
    0.85
    mode
    0.85
    mong
    0.81
    ju
    0.81
    naires
    0.79
    roots
    0.78
    buster
    0.78
    ie
    0.76
    Activations Density 0.031%

    No Known Activations