© 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. 6-RES-JB
    11. 17190
    Prev
    Next
    INDEX
    Explanations

    brand logos or logos with possible design changes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "logo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.76
    kus
    -0.75
     Ago
    -0.73
    neau
    -0.72
    astern
    -0.70
    hurst
    -0.68
    hower
    -0.65
     Lank
    -0.62
    auld
    -0.62
     experien
    -0.61
    POSITIVE LOGITS
     logos
    1.00
     logo
    0.95
     Logo
    0.89
     Doodle
    0.85
    FILE
    0.75
    plates
    0.74
    inates
    0.73
    matic
    0.72
     slogan
    0.71
    olor
    0.70
    Activations Density 0.037%

    No Known Activations