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. 8-RES-JB
    6. 19674
    Prev
    Next
    INDEX
    Explanations

    mentions of the German newspaper "Süddeutsche Zeitung."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "de" in various contexts, indicating a focus on German language usage or reference to German entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.76
    sit
    -0.75
    hetti
    -0.70
    icals
    -0.70
    allery
    -0.67
    ieri
    -0.66
    annis
    -0.65
    ivities
    -0.65
    ographs
    -0.64
    icago
    -0.64
    POSITIVE LOGITS
    utsche
    1.32
    ploy
    1.26
    leted
    1.24
    cember
    1.22
    legate
    1.20
    legates
    1.16
    hyde
    1.11
    bris
    1.10
    FAULT
    1.04
    cker
    1.03
    Activations Density 0.026%

    No Known Activations