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. 11-RES-JB
    6. 10928
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the extent or scope of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to comprehensiveness and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAN
    -0.77
    ilon
    -0.73
    rious
    -0.67
    ILLE
    -0.66
     Keeper
    -0.63
    Hunt
    -0.63
     Tycoon
    -0.62
    illard
    -0.62
    Fight
    -0.61
    illation
    -0.60
    POSITIVE LOGITS
    sheet
    1.43
    ening
    1.32
    sheets
    1.24
    ened
    1.14
    side
    1.12
     strokes
    1.12
     spectrum
    1.10
    sword
    1.10
     swath
    1.05
    cloth
    0.98
    Activations Density 0.046%

    No Known Activations