© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11061
    Prev
    Next
    INDEX
    Explanations

    phrases containing the term "fold"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe complexity and clarity in explanations or arguments

    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
     Instr
    -0.74
     renovations
    -0.70
     broom
    -0.66
     shuttle
    -0.60
     disbanded
    -0.58
     manned
    -0.58
     Rolls
    -0.58
     wardrobe
    -0.56
    yles
    -0.56
     refurb
    -0.56
    POSITIVE LOGITS
    :[
    0.97
    .
    0.96
    :
    0.92
    .):
    0.92
     because
    0.91
     insofar
    0.89
    *:
    0.87
     considering
    0.87
     empir
    0.83
    :-
    0.83
    Activations Density 0.290%

    No Known Activations