© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 825
    Prev
    Next
    INDEX
    Explanations

    quantitative information such as numbers and ranges

    oai_token-act-pair · gpt-3.5-turbo

    numeric data related to estimates and ranges

    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
    uthor
    -0.82
    arty
    -0.62
    urgical
    -0.62
    idan
    -0.61
    agher
    -0.59
    actionDate
    -0.59
    OUP
    -0.59
    Day
    -0.59
    oy
    -0.58
     Day
    -0.58
    POSITIVE LOGITS
     vicinity
    1.17
     ballpark
    1.11
     range
    1.08
     realm
    1.06
     realms
    1.01
     twenties
    1.01
     teens
    0.98
    undreds
    0.93
     ranges
    0.87
     percentile
    0.86
    Activations Density 0.122%

    No Known Activations