© 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. 10-RES-JB
    11. 8552
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to news articles or headlines containing the word "Gallery"

    oai_token-act-pair · gpt-3.5-turbo

    instances of references to galleries or gallery-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.51
     tweeting
    -0.48
     answ
    -0.47
    Rated
    -0.46
     wand
    -0.45
     divides
    -0.45
     sourcing
    -0.44
     nails
    -0.44
     brow
    -0.44
    âĸº
    -0.43
    POSITIVE LOGITS
    eming
    0.65
    senal
    0.64
    thia
    0.60
    cedented
    0.57
    lins
    0.56
     ILCS
    0.52
    iminary
    0.52
    =-=-=-=-=-=-=-=-
    0.51
    arate
    0.51
    throp
    0.49
    Activations Density 0.398%

    No Known Activations