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. 8317
    Prev
    Next
    INDEX
    Explanations

    Scandinavian characters and words

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols, particularly special characters resembling letters or diacritics

    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
    DonaldTrump
    -0.74
     Crus
    -0.71
    ORED
    -0.69
    IFIED
    -0.63
     Throne
    -0.61
    IONS
    -0.60
    ively
    -0.60
    arily
    -0.59
     kernels
    -0.58
    Beat
    -0.57
    POSITIVE LOGITS
    rd
    1.20
    rg
    1.17
    nda
    1.14
    rm
    1.12
    rn
    1.11
    ng
    1.06
    der
    1.02
    rent
    1.02
    dra
    1.01
    sta
    1.01
    Activations Density 0.051%

    No Known Activations