© 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 EvalsExportsinterp-engineNEWAPI 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. 20763
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of people and publications

    oai_token-act-pair · gpt-3.5-turbo

    names of people associated with photography or media

    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
     pronouns
    -0.70
    âĢķ
    -0.68
    rencies
    -0.65
     verbs
    -0.65
     âĢķ
    -0.62
    rums
    -0.62
    tics
    -0.62
    answered
    -0.59
    _>
    -0.58
    %:
    -0.58
    POSITIVE LOGITS
     Associated
    1.15
     NYT
    0.94
     Chronicle
    0.91
     AFP
    0.90
     Getty
    0.88
     Staff
    0.84
     Flickr
    0.83
     File
    0.81
     AP
    0.81
    Flickr
    0.79
    Activations Density 0.043%

    No Known Activations