© 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. 8-RES-JB
    11. 4580
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the artist "Picasso"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Picasso" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorely
    -0.71
     Goo
    -0.66
     ultrasound
    -0.65
     winds
    -0.63
     unregulated
    -0.62
    EEP
    -0.62
     booming
    -0.60
    orf
    -0.59
     ward
    -0.59
     Nanto
    -0.58
    POSITIVE LOGITS
    colo
    1.32
    nic
    1.10
    asso
    1.08
    ross
    0.99
    atin
    0.92
    alog
    0.91
    asus
    0.91
    amera
    0.91
    Pic
    0.86
    chu
    0.86
    Activations Density 0.035%

    No Known Activations