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. 9691
    Prev
    Next
    INDEX
    Explanations

    titles or references to the website IMDb (Internet Movie Database)

    oai_token-act-pair · gpt-3.5-turbo

    the acronym "IM" in various contexts related to film or media

    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
    issan
    -0.74
    quez
    -0.73
    king
    -0.68
    lain
    -0.68
    velt
    -0.66
    ledge
    -0.66
    isson
    -0.63
    sea
    -0.63
    omore
    -0.62
    lies
    -0.61
    POSITIVE LOGITS
    HO
    1.25
    PLIC
    1.22
    PLE
    1.21
    AX
    1.17
    Db
    1.12
    MED
    1.10
    AGE
    1.09
    PORT
    1.08
    PROV
    1.07
    PLIED
    1.06
    Activations Density 0.025%

    No Known Activations