Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10318
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health conditions and socio-political statistics

    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
     Crusade
    -0.64
     miscon
    -0.58
    tnc
    -0.56
    hiro
    -0.55
    Ô
    -0.53
    ¯¯¯¯¯¯¯¯
    -0.53
    ylan
    -0.52
    ameless
    -0.52
    Dub
    -0.52
    Reviewer
    -0.52
    POSITIVE LOGITS
     compared
    1.30
     (>
    1.00
     âī¥
    1.00
     (%
    0.98
     (<
    0.94
     annually
    0.91
     versus
    0.89
     apiece
    0.88
     whereas
    0.87
     Percentage
    0.87
    Activations Density 0.368%

    No Known Activations