© 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. 7-RES-JB
    11. 20582
    Prev
    Next
    INDEX
    Explanations

    information or content presented in a structured format beneath a specific heading

    oai_token-act-pair · gpt-3.5-turbo

    introductory phrases or sections in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.71
    ãĥı
    -0.71
    ãĤ£
    -0.64
    natureconservancy
    -0.62
    ãĥ¼ãĥĨ
    -0.61
    itar
    -0.60
    Deal
    -0.58
    SU
    -0.57
    idad
    -0.56
    mong
    -0.56
    POSITIVE LOGITS
    ground
    0.91
     Thumbnails
    0.90
    neath
    0.79
    fter
    0.76
    noon
    0.75
    deck
    0.74
     screenshot
    0.73
    ileaks
    0.73
    İĭ
    0.70
     depicts
    0.70
    Activations Density 0.035%

    No Known Activations