© 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. 747
    Prev
    Next
    INDEX
    Explanations

    negatively connotated words or word parts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ten" and its variations

    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
    ****************
    -0.65
     jerk
    -0.63
    TextColor
    -0.63
    Reviewer
    -0.62
     Indust
    -0.58
    ħĭ
    -0.57
    HY
    -0.57
     DRAG
    -0.56
    CVE
    -0.55
    BOOK
    -0.53
    POSITIVE LOGITS
    acity
    1.71
    acious
    1.62
    aciously
    1.59
    uous
    1.57
    uously
    1.49
    ured
    1.36
    ancies
    1.24
    orio
    1.21
    ements
    1.20
    anted
    1.16
    Activations Density 0.031%

    No Known Activations