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. 6-RES-JB
    6. 12392
    Prev
    Next
    INDEX
    Explanations

    keywords related to various parts of the human body, especially the brain, muscle, blood, and heart

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical and biological materials and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.98
    nces
    -0.93
    ilitary
    -0.90
    女
    -0.84
    å§«
    -0.79
    odus
    -0.74
    ometimes
    -0.73
    orthern
    -0.73
    arity
    -0.73
    ownt
    -0.73
    POSITIVE LOGITS
     ®
    0.70
    ,[
    0.69
    ®,
    0.68
    like
    0.68
     tissue
    0.67
     pH
    0.66
    âĢIJ
    0.65
     rad
    0.65
    AMY
    0.65
     nucle
    0.64
    Activations Density 0.637%

    No Known Activations