© 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. 7835
    Prev
    Next
    INDEX
    Explanations

    numerical values with an emphasis on fractions and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their relationships in contexts like statistics or performance

    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
    —
    -0.72
    ,—
    -0.72
    ,[
    -0.70
    ;
    -0.69
    ,
    -0.69
    ,'
    -0.68
    ?
    -0.67
     âĢķ
    -0.67
    ––
    -0.66
    >,
    -0.65
    POSITIVE LOGITS
    imentary
    0.57
    bernatorial
    0.56
    lesiastical
    0.53
     havoc
    0.52
    imental
    0.51
    ileged
    0.50
    osponsors
    0.50
    ravings
    0.50
    çĶ°
    0.49
    izens
    0.49
    Activations Density 1.008%

    No Known Activations