© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    phrases indicating readiness or preparation for specific future events

    oai_token-act-pair · gpt-3.5-turbo

    situations that involve conditions or parameters that might affect certain outcomes or actions

    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
     ILCS
    -0.68
    tein
    -0.68
    akia
    -0.58
    rod
    -0.56
    hua
    -0.55
    rahim
    -0.55
    roots
    -0.54
    utenberg
    -0.54
    SHARE
    -0.53
    each
    -0.52
    POSITIVE LOGITS
     arise
    1.02
     needed
    1.01
     disple
    1.00
    needed
    0.99
     warranted
    0.98
     unforeseen
    0.93
     fal
    0.91
     malf
    0.91
     misfortune
    0.90
     arises
    0.88
    Activations Density 0.273%

    No Known Activations