© 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. 20469
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a list or sequence of items

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "as follows" and variations indicating lists or explanations

    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
     sweat
    -0.55
    ?),
    -0.52
    Ħ¢
    -0.51
     damned
    -0.51
     slammed
    -0.51
    ?).
    -0.51
    iami
    -0.50
     rebound
    -0.50
     shortages
    -0.50
    ©¶æ¥µ
    -0.50
    POSITIVE LOGITS
    :[
    1.49
    :(
    1.23
    :-
    1.23
    :
    1.21
    *:
    1.20
    :"
    1.15
    .:
    1.04
    :{
    1.03
    :,
    0.99
    :'
    0.94
    Activations Density 0.137%

    No Known Activations