© 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. 15989
    Prev
    Next
    INDEX
    Explanations

    phrases or patterns denoting a range or sequence of numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical data, particularly those involving hyphenated numbers

    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
     wedd
    -0.67
     Beauty
    -0.65
     Apache
    -0.64
     fifty
    -0.63
     Byrne
    -0.60
     Bates
    -0.60
     domin
    -0.60
     Maced
    -0.60
     Psycho
    -0.60
     hon
    -0.59
    POSITIVE LOGITS
    liter
    1.25
    sided
    1.22
    minute
    1.20
    degree
    1.18
    year
    1.18
    percent
    1.16
    digit
    1.16
    hour
    1.12
    inch
    1.11
    pointers
    1.10
    Activations Density 0.060%

    No Known Activations