© 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. 1429
    Prev
    Next
    INDEX
    Explanations

    keywords related to strategies, medical procedures, technology, economics, and politics

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to strategic implications and societal structures

    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
     YES
    -0.70
    requisite
    -0.66
    blank
    -0.65
    clusion
    -0.64
    =~
    -0.64
     stating
    -0.63
    mberg
    -0.63
    ¶ħ
    -0.63
    urances
    -0.62
    none
    -0.61
    POSITIVE LOGITS
     interacts
    1.31
     fared
    1.31
     compares
    1.21
     relates
    1.16
     affects
    1.15
     interacted
    1.14
     differs
    1.13
     stacks
    1.11
     reacted
    1.10
     reacts
    1.09
    Activations Density 0.223%

    No Known Activations