© 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. 0-RES-JB
    11. 5375
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual depiction or representation

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of portraits

    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
    onge
    -0.78
    SN
    -0.68
    aba
    -0.66
     Hig
    -0.65
    UU
    -0.64
    bra
    -0.61
    chy
    -0.60
     McCorm
    -0.60
     Lem
    -0.59
     Dri
    -0.58
    POSITIVE LOGITS
     portrait
    4.03
     portraits
    3.12
    rait
    1.68
    raits
    1.53
     picture
    1.53
     caricature
    1.52
     photograph
    1.51
     biography
    1.40
     painting
    1.38
     snapshot
    1.36
    Activations Density 0.017%

    No Known Activations