© 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. 1205
    Prev
    Next
    INDEX
    Explanations

    instances where multiple components or entities are being used or considered together

    oai_token-act-pair · gpt-3.5-turbo

    situations involving multiple entities or actions occurring simultaneously

    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
    esan
    -0.81
    ®,
    -0.63
     Secondly
    -0.63
    \<
    -0.62
    ãĤĮ
    -0.61
    enta
    -0.58
    ©
    -0.57
    agger
    -0.57
    oug
    -0.57
    ecause
    -0.56
    POSITIVE LOGITS
     identical
    1.39
     simultaneously
    1.39
     different
    1.38
    same
    1.27
     separate
    1.26
     differing
    1.25
     alike
    1.22
     concurrently
    1.21
     unison
    1.20
     simultaneous
    1.19
    Activations Density 0.525%

    No Known Activations