© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1367
    Prev
    Next
    INDEX
    Explanations

    specific locations or places associated with individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and the associated events involving specific groups of people

    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
     Horizon
    -0.76
     Cancel
    -0.70
    notations
    -0.69
    ickr
    -0.69
     Respons
    -0.65
    blance
    -0.65
    notice
    -0.65
     Waves
    -0.64
    20439
    -0.62
    ++;
    -0.62
    POSITIVE LOGITS
     resided
    1.21
     resides
    1.16
     reside
    1.14
     awaited
    1.03
     lived
    0.97
     sheltered
    0.89
     awaits
    0.88
     worshipped
    0.88
     congreg
    0.87
     lodged
    0.85
    Activations Density 0.151%

    No Known Activations