© 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. 16124
    Prev
    Next
    INDEX
    Explanations

    streets and locations within documents

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to business and finance

    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
     newfound
    -0.54
    yssey
    -0.53
    interstitial
    -0.52
     hypothesized
    -0.52
     Canaver
    -0.51
     longtime
    -0.51
    SCP
    -0.46
    ¿½
    -0.45
    iculty
    -0.44
    shapeshifter
    -0.44
    POSITIVE LOGITS
     etc
    0.98
     whilst
    0.89
     and
    0.81
     &
    0.77
     doesnt
    0.76
     AND
    0.71
     instead
    0.71
     or
    0.69
     Whilst
    0.69
    [/
    0.68
    Activations Density 0.903%

    No Known Activations