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. 11-RES-JB
    6. 24313
    Prev
    Next
    INDEX
    Explanations

    requests to subscribe to newsletters or receive news alerts

    oai_token-act-pair · gpt-3.5-turbo

    question marks in the text, indicating inquiries or prompts for engagement

    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
    beit
    -0.66
    liest
    -0.63
    fram
    -0.63
    esome
    -0.60
    ãĤ´ãĥ³
    -0.56
    arios
    -0.56
    hof
    -0.55
    frames
    -0.55
    men
    -0.55
    mens
    -0.54
    POSITIVE LOGITS
     Subscribe
    0.81
     Email
    0.75
     Sign
    0.72
     Join
    0.70
     Transcript
    0.68
     Click
    0.65
     Try
    0.65
    utm
    0.64
     subscribe
    0.63
    awk
    0.62
    Activations Density 0.016%

    No Known Activations