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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 12258
    Prev
    Next
    INDEX
    Explanations

    promotional text prompting readers to check out or subscribe to something

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to subscribing or engaging with 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
     Quote
    -0.66
    aeda
    -0.65
     Specifications
    -0.65
     PLA
    -0.65
     Classification
    -0.65
    enhagen
    -0.64
     FAC
    -0.63
    fram
    -0.61
    escription
    -0.61
     Modes
    -0.60
    POSITIVE LOGITS
    entimes
    0.71
    leground
    0.64
    à¤
    0.64
    bleacher
    0.60
    attered
    0.59
    attering
    0.59
    olly
    0.59
    Travel
    0.58
    leans
    0.56
    tle
    0.55
    Activations Density 0.042%

    No Known Activations