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. 4-RES-JB
    6. 8755
    Prev
    Next
    INDEX
    Explanations

    mentions of research papers being published in various journals

    oai_token-act-pair · gpt-3.5-turbo

    references to academic publications

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

    No Comments

    Negative Logits
    llan
    -0.91
    vette
    -0.83
    xa
    -0.78
    hart
    -0.77
    zh
    -0.70
    ovan
    -0.69
    ggle
    -0.68
    heed
    -0.67
    nea
    -0.66
    aho
    -0.66
    POSITIVE LOGITS
    lishing
    1.06
    lisher
    0.99
     excerpts
    0.92
    lishes
    0.79
     newsp
    0.78
    DragonMagazine
    0.75
    Ô
    0.75
     behavi
    0.74
    gres
    0.74
    çīĪ
    0.71
    Activations Density 0.025%

    No Known Activations