© 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. 8
    Prev
    Next
    INDEX
    Explanations

    scientific research findings or results

    oai_token-act-pair · gpt-3.5-turbo

    references to research findings and results in scientific studies

    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
     ILCS
    -0.72
    Boss
    -0.68
     Faces
    -0.66
     likes
    -0.66
    tis
    -0.65
     hates
    -0.65
     actionGroup
    -0.64
     sacrific
    -0.64
     remembers
    -0.63
     eternity
    -0.63
    POSITIVE LOGITS
     suggest
    1.29
     imply
    1.26
     indicate
    1.26
     underscore
    1.23
     demonstrate
    1.19
     contradict
    1.18
     confirm
    1.17
     refute
    1.16
     reinforce
    1.15
     illustrate
    1.11
    Activations Density 0.070%

    No Known Activations