© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 10302
    Prev
    Next
    INDEX
    Explanations

    terms related to breaking news and newsletters

    oai_token-act-pair · gpt-3.5-turbo

    references to breaking news

    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
     nostalg
    -0.71
    ãĤ§
    -0.69
    vag
    -0.66
     sul
    -0.63
    rendered
    -0.63
    çĶŁ
    -0.61
    urat
    -0.60
     pse
    -0.60
    ikan
    -0.59
    ãĥĺ
    -0.59
    POSITIVE LOGITS
     Emails
    1.47
     Email
    0.77
     Desk
    0.76
     VIDEOS
    0.70
     EXT
    0.67
     Videos
    0.66
     Photos
    0.66
     Mub
    0.66
     Breaking
    0.65
    Desk
    0.65
    Activations Density 0.020%

    No Known Activations