© 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. 1-RES-JB
    11. 24073
    Prev
    Next
    INDEX
    Explanations

    words related to art or artistic activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 'art.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.70
     Benghazi
    -0.68
     Philly
    -0.66
     Cyprus
    -0.63
     sidx
    -0.59
     Ti
    -0.59
     Crosby
    -0.58
     polar
    -0.58
    pora
    -0.58
     Grizzlies
    -0.58
    POSITIVE LOGITS
    art
    1.33
    ifact
    1.11
    emis
    1.04
    esian
    0.96
    artist
    0.96
    ificial
    0.96
    isans
    0.95
    illery
    0.95
    works
    0.93
    arts
    0.92
    Activations Density 0.006%

    No Known Activations