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. 1-RES-JB
    6. 19942
    Prev
    Next
    INDEX
    Explanations

    organizations or entities with the word "chel" or "cil"

    oai_token-act-pair · gpt-3.5-turbo

    words related to hierarchical rankings or tiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rated
    -1.07
    ŃĶ
    -0.70
     razor
    -0.67
    Reviewer
    -0.64
    regon
    -0.64
     Prediction
    -0.60
    GGGGGGGG
    -0.60
    DEM
    -0.60
    Rating
    -0.57
     dement
    -0.57
    POSITIVE LOGITS
    chel
    1.04
    vous
    0.90
    bach
    0.90
    theless
    0.85
    lean
    0.85
    brates
    0.84
    le
    0.84
    witz
    0.79
    bilt
    0.78
    sea
    0.78
    Activations Density 0.011%

    No Known Activations