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. 7-RES-JB
    6. 7637
    Prev
    Next
    INDEX
    Explanations

    mentions of specific cities or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or events with significant impacts

    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
     destro
    -0.81
    ÃĥÃĤÃĥÃĤ
    -0.77
    Ħ¢
    -0.77
     unden
    -0.76
     charact
    -0.75
     likeness
    -0.75
    £ı
    -0.71
     proport
    -0.71
    DeliveryDate
    -0.71
     practition
    -0.70
    POSITIVE LOGITS
     HUD
    0.70
     NOTICE
    0.70
    Reviewer
    0.69
     Diary
    0.69
    Subject
    0.66
     Discussion
    0.66
     Altern
    0.65
     Related
    0.64
     Hang
    0.64
    ":""},{"
    0.64
    Activations Density 0.076%

    No Known Activations