© 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. 9469
    Prev
    Next
    INDEX
    Explanations

    exclamatory phrases indicating certainty or invitation

    oai_token-act-pair · gpt-3.5-turbo

    the character 'Ļ' and its variations

    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
     Laurent
    -0.66
     highlights
    -0.64
     heads
    -0.61
     airs
    -0.60
     scraps
    -0.60
     spins
    -0.59
     offsets
    -0.59
     friction
    -0.59
     crosses
    -0.58
     SHARES
    -0.57
    POSITIVE LOGITS
    ll
    1.28
    re
    1.08
    ve
    1.08
    must
    1.07
    shall
    1.05
    tube
    1.02
    want
    1.01
    know
    1.01
    should
    0.98
    have
    0.96
    Activations Density 0.105%

    No Known Activations