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

    Neuronpedia

    Jacobian LensNEW
    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. 14939
    Prev
    Next
    INDEX
    Explanations

    scientific or academic studies and research

    oai_token-act-pair · gpt-3.5-turbo

    references to previous research studies and their findings

    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
     Strongh
    -0.71
    eworld
    -0.65
    terday
    -0.64
     Ruler
    -0.64
     Tire
    -0.63
     Mahjong
    -0.63
    cers
    -0.62
     Theft
    -0.62
    BuyableInstoreAndOnline
    -0.60
     Defender
    -0.60
    POSITIVE LOGITS
     examining
    1.26
     investigating
    1.23
     demonstrating
    1.22
     evaluating
    1.22
     comparing
    1.14
     assessing
    1.13
     documenting
    1.08
     showing
    1.06
     exploring
    1.05
     conducted
    1.05
    Activations Density 0.114%

    No Known Activations