© 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. 21786
    Prev
    Next
    INDEX
    Explanations

    specific entities or individuals, such as sports teams or players, mentioned in a journalistic context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The" or phrases that refer to specific subjects or events

    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
    EVA
    -0.77
    NetMessage
    -0.76
    Interstitial
    -0.73
    APD
    -0.73
    acci
    -0.69
    Ops
    -0.69
    pai
    -0.67
    ipedia
    -0.66
    Episode
    -0.66
    ageddon
    -0.66
    POSITIVE LOGITS
     versatile
    1.14
     youngster
    1.13
     29
    1.07
     26
    1.07
     Frenchman
    1.04
     31
    1.04
     undrafted
    1.03
     34
    1.01
     27
    1.01
     midfielder
    1.00
    Activations Density 0.131%

    No Known Activations