© 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. 10726
    Prev
    Next
    INDEX
    Explanations

    locations and transportation-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups in various contexts

    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
    ottest
    -0.56
    changed
    -0.55
    pots
    -0.54
     Consent
    -0.53
    cknow
    -0.52
    ITNESS
    -0.51
    Lat
    -0.50
    lder
    -0.50
     actionGroup
    -0.50
    orest
    -0.50
    POSITIVE LOGITS
     away
    1.29
     into
    1.25
     toward
    1.25
     onto
    1.19
     towards
    1.18
     onward
    1.10
     hither
    1.08
     INTO
    1.06
     overboard
    1.03
     ashore
    1.03
    Activations Density 0.349%

    No Known Activations