© 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. 11-RES-JB
    11. 17379
    Prev
    Next
    INDEX
    Explanations

    economic data related to percentages and numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a quantitative increase or measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resy
    -0.62
    ookie
    -0.61
    ebus
    -0.59
    acci
    -0.56
    VPN
    -0.56
    Acknowled
    -0.56
    iHUD
    -0.56
    ä½ľ
    -0.55
    Dro
    -0.55
    KNOWN
    -0.54
    POSITIVE LOGITS
     accommodate
    1.12
     compensate
    1.11
     encompass
    1.06
     include
    1.01
     coincide
    0.97
     exceed
    0.92
     become
    0.92
     resemble
    0.89
     justify
    0.88
     meet
    0.87
    Activations Density 0.087%

    No Known Activations