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. 14069
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shell" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "shell" in various contexts

    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
    é¾įå
    -0.86
     ILCS
    -0.69
    ————————————————
    -0.68
    20439
    -0.66
    RESULTS
    -0.65
    committee
    -0.65
    è¡
    -0.63
    HCR
    -0.63
    Population
    -0.62
     Aad
    -0.62
    POSITIVE LOGITS
    shell
    1.21
     shells
    1.18
     shell
    1.11
    fish
    1.10
     casing
    0.99
    shock
    0.95
     reefs
    0.85
     cas
    0.84
    brook
    0.81
    bash
    0.80
    Activations Density 0.008%

    No Known Activations