© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7909
    Prev
    Next
    INDEX
    Explanations

    words related to numbers or numerical expressions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data presented in a "X percent" format

    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
     AVG
    -0.76
    ãĤ¯
    -0.75
    ãĥ£
    -0.74
    ãĤ¡
    -0.72
     Aether
    -0.71
    HCR
    -0.68
    achu
    -0.67
     Duo
    -0.67
    rawdownloadcloneembedreportprint
    -0.67
     Fiesta
    -0.67
    POSITIVE LOGITS
    eight
    1.16
    percent
    1.15
    six
    1.11
    five
    1.08
    year
    1.08
    seven
    1.07
    four
    1.07
    nine
    1.04
    second
    1.04
    two
    1.03
    Activations Density 0.040%

    No Known Activations