© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9095
    Prev
    Next
    INDEX
    Explanations

    language related to art or creativity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to artistic and creative expression

    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
     Contra
    -0.72
    upon
    -0.71
    apters
    -0.70
    DAY
    -0.69
     Vikings
    -0.68
    nu
    -0.66
     Tucker
    -0.65
    aptic
    -0.64
    Phones
    -0.63
    ighed
    -0.63
    POSITIVE LOGITS
     artistic
    1.08
    isans
    0.86
     galleries
    0.86
     gymn
    0.86
     aesthetic
    0.85
     artist
    0.85
    Artist
    0.83
     arts
    0.82
     artwork
    0.82
    ¥ŀ
    0.82
    Activations Density 0.008%

    No Known Activations