© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10286
    Prev
    Next
    INDEX
    Explanations

    phrases related to concept art and artwork

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of art and artistic concepts

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

    No Comments

    Negative Logits
    ctr
    -0.83
    SPONSORED
    -0.79
    edience
    -0.75
    olean
    -0.74
    cffff
    -0.72
    olate
    -0.72
    vernment
    -0.72
    ught
    -0.70
     econom
    -0.70
    bern
    -0.69
    POSITIVE LOGITS
    heet
    0.91
     drawings
    0.84
     IMAGES
    0.84
     artwork
    0.84
     illustration
    0.83
     rendering
    0.81
     render
    0.81
     illustrations
    0.80
     depicting
    0.80
     sleeves
    0.80
    Activations Density 0.074%

    No Known Activations