© 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. 12503
    Prev
    Next
    INDEX
    Explanations

    references to hands-on activities or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving hands-on experiences or activities

    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
     Albion
    -0.77
    rama
    -0.67
    AMI
    -0.64
     WARN
    -0.64
    VERS
    -0.61
     Cinem
    -0.59
    alias
    -0.58
    ICO
    -0.57
    actionDate
    -0.56
    illery
    -0.56
    POSITIVE LOGITS
    pring
    1.29
    ets
    1.10
    ome
    1.00
    peed
    0.98
    pace
    0.94
    omen
    0.91
    cript
    0.91
    pread
    0.91
    chool
    0.90
    omes
    0.90
    Activations Density 0.042%

    No Known Activations