© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18475
    Prev
    Next
    INDEX
    Explanations

    in-depth analysis or coverage of various topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of in-depth analysis or discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anda
    -0.74
    hett
    -0.72
    iah
    -0.71
    eer
    -0.68
    immune
    -0.66
    avis
    -0.64
    iggs
    -0.63
    ques
    -0.63
     Allaah
    -0.62
    orious
    -0.61
    POSITIVE LOGITS
    depth
    1.01
    çīĪ
    0.88
     Depth
    0.87
     penetration
    0.82
     detail
    0.78
     depth
    0.77
     examination
    0.75
     insight
    0.74
    terday
    0.73
     confir
    0.72
    Activations Density 0.006%

    No Known Activations