© 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. 13519
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity, such as "up to"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "up"

    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
    Maker
    -0.67
    ________________________
    -0.64
    gee
    -0.62
    TY
    -0.61
    9999
    -0.60
    ====
    -0.60
    999
    -0.58
     Munich
    -0.58
    [/
    -0.57
     Geneva
    -0.57
    POSITIVE LOGITS
    graded
    1.24
    grades
    1.23
    grading
    1.23
    stairs
    1.15
    dates
    1.12
    dating
    1.01
    raised
    0.94
    votes
    0.93
    rights
    0.91
    ended
    0.89
    Activations Density 0.069%

    No Known Activations