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. 16001
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    structured social media or online interaction cues

    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
    paces
    -0.82
     Mines
    -0.76
    anza
    -0.73
     Cent
    -0.72
    abouts
    -0.71
    tk
    -0.69
    recy
    -0.66
     manoeuv
    -0.66
    cuts
    -0.66
    hement
    -0.66
    POSITIVE LOGITS
    ãĥŁ
    0.67
    pmwiki
    0.62
    à¼
    0.60
    ixture
    0.59
    inion
    0.59
    malink
    0.58
     screenplay
    0.57
    Í
    0.56
     provoke
    0.54
    Ü
    0.54
    Activations Density 0.131%

    No Known Activations