© 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. 0-RES-JB
    6. 2904
    Prev
    Next
    INDEX
    Explanations

    mentions of various forms of art

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reward
    -0.77
    upon
    -0.66
    IP
    -0.65
    oby
    -0.64
    Driver
    -0.64
    tracking
    -0.63
    OTAL
    -0.63
    GM
    -0.62
     Recall
    -0.61
    ulnerability
    -0.60
    POSITIVE LOGITS
     arts
    3.96
     Arts
    2.82
     art
    1.88
     humanities
    1.66
     sciences
    1.60
     artists
    1.46
     artistic
    1.42
     Artists
    1.37
     artist
    1.36
     Art
    1.23
    Activations Density 0.019%

    No Known Activations