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. 0-RES-JB
    6. 15902
    Prev
    Next
    INDEX
    Explanations

    phrases related to public relations or PR activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to public relations and media mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llah
    -0.82
     beetle
    -0.78
    asse
    -0.73
    uddin
    -0.72
    aldi
    -0.69
    chwitz
    -0.66
    iHUD
    -0.64
    azes
    -0.64
    ãĤ®
    -0.63
     beetles
    -0.62
    POSITIVE LOGITS
     PR
    3.59
    PR
    2.07
     PUBLIC
    1.26
     HR
    1.23
     QU
    1.22
     publicity
    1.20
     PL
    1.17
     RE
    1.16
     PROG
    1.15
     CR
    1.13
    Activations Density 0.015%

    No Known Activations