© 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. 7186
    Prev
    Next
    INDEX
    Explanations

    fractions or portions specified numerically in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proportions or fractions of groups

    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
     Ready
    -0.68
     drama
    -0.67
     Illum
    -0.65
     Dickinson
    -0.64
     Lana
    -0.62
     Kafka
    -0.62
     LO
    -0.60
     Carry
    -0.60
     competition
    -0.59
     Drama
    -0.59
    POSITIVE LOGITS
    thirds
    1.84
    dozen
    1.49
    third
    1.47
    fif
    1.46
    fifth
    1.36
    quarters
    1.34
    half
    1.34
    fourth
    1.33
    percent
    1.29
     thirds
    1.27
    Activations Density 0.051%

    No Known Activations