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. 8-RES-JB
    6. 9573
    Prev
    Next
    INDEX
    Explanations

    adjectives related to surrealism

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to surrealism and sensationalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Caesar
    -0.66
     Thor
    -0.60
     Moons
    -0.59
    lihood
    -0.59
     Roc
    -0.58
     Âł Âł Âł Âł
    -0.57
    kens
    -0.57
     Io
    -0.57
    robe
    -0.57
    peak
    -0.57
    POSITIVE LOGITS
    ists
    2.56
    ist
    2.55
    ism
    2.47
    istic
    2.23
    istically
    2.08
    isms
    1.76
    ary
    1.67
    istical
    1.66
    IST
    1.65
    ISM
    1.60
    Activations Density 0.219%

    No Known Activations