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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10545
    Prev
    Next
    INDEX
    Explanations

    mentions of different forms and aspects of art, such as painting, architecture, and sculpture

    oai_token-act-pair · gpt-3.5-turbo

    references to art in various contexts

    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
     Wyoming
    -0.70
     DN
    -0.69
     Ingram
    -0.63
    pora
    -0.63
     McGee
    -0.62
     VT
    -0.62
     Chiefs
    -0.62
     Bagg
    -0.61
     Somalia
    -0.61
    inki
    -0.61
    POSITIVE LOGITS
    istry
    1.53
    isans
    1.38
    emis
    1.36
    ifice
    1.31
    esian
    1.28
    works
    1.27
    illery
    1.17
    ifacts
    1.06
    ificial
    0.99
    work
    0.98
    Activations Density 0.021%

    No Known Activations