© 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. 9-RES-JB
    11. 15505
    Prev
    Next
    INDEX
    Explanations

    usernames or handles with 'ub' in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ub" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.69
     drift
    -0.69
     ORIG
    -0.66
     Atlantic
    -0.66
     Clash
    -0.64
     ultraviolet
    -0.62
     ozone
    -0.62
     butterflies
    -0.61
     Irma
    -0.60
     Overt
    -0.60
    POSITIVE LOGITS
    lishing
    1.36
    ilee
    1.27
    ilant
    1.24
    lique
    1.22
    rious
    1.21
    bing
    1.17
    bish
    1.12
    lisher
    1.11
    lish
    1.11
    bles
    1.08
    Activations Density 0.030%

    No Known Activations