Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 10484
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "De."

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the placeholder token, indicating the end of text or lack of relevant content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CPC
    -0.69
     Showdown
    -0.64
    INGS
    -0.62
     sidx
    -0.61
     logger
    -0.59
     Cobra
    -0.59
    ãĤ¼ãĤ¦ãĤ¹
    -0.59
     BaseType
    -0.58
     Everywhere
    -0.58
     exhibits
    -0.58
    POSITIVE LOGITS
    legate
    1.26
    arest
    1.20
    utsch
    1.19
    legates
    1.19
    forestation
    1.19
    bris
    1.14
    cember
    1.14
    gradation
    1.11
    eper
    1.11
    leted
    1.10
    Activations Density 0.024%

    No Known Activations