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. 10-RES-JB
    6. 1769
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names starting with the letter "W"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'W' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prelude
    -0.75
     psy
    -0.72
     conscientious
    -0.64
     finite
    -0.61
     coupled
    -0.61
     vested
    -0.60
     bitters
    -0.60
     Martian
    -0.60
     skepticism
    -0.60
     headache
    -0.58
    POSITIVE LOGITS
    idespread
    1.30
    ITNESS
    1.28
    ASHINGTON
    1.24
    ALK
    1.23
    reck
    1.22
    OOD
    1.21
    rote
    1.21
    ounded
    1.18
    orthy
    1.18
    IRED
    1.17
    Activations Density 0.027%

    No Known Activations