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. 3-RES-JB
    6. 22169
    Prev
    Next
    INDEX
    Explanations

    words related to mushrooms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mushrooms and related culinary terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.78
     dental
    -0.74
     cradle
    -0.70
     confession
    -0.68
     latex
    -0.66
     Viking
    -0.66
     cyn
    -0.65
     prol
    -0.65
     liner
    -0.65
    ãĥ¼ãĥĨ
    -0.64
    POSITIVE LOGITS
    rooms
    1.18
    imoto
    1.09
     Mush
    1.04
    ishi
    0.95
    raf
    0.93
    adow
    0.93
    etsu
    0.92
    awar
    0.91
    ires
    0.91
    ira
    0.90
    Activations Density 0.008%

    No Known Activations