© 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. 4-RES-JB
    11. 13486
    Prev
    Next
    INDEX
    Explanations

    locations, especially those related to battles or historical events

    oai_token-act-pair · gpt-3.5-turbo

    names of places and entities, particularly with the suffix "amo" and variations of "Nikola" and "isco."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wealth
    -0.79
    meal
    -0.77
     ADS
    -0.73
    risome
    -0.72
    ties
    -0.71
    lessness
    -0.70
     ASC
    -0.70
    acerb
    -0.69
    school
    -0.68
    sworth
    -0.67
    POSITIVE LOGITS
    orthy
    0.84
    Bio
    0.81
    etry
    0.76
    osity
    0.76
    ovies
    0.74
     Dra
    0.73
    antle
    0.73
    oths
    0.72
    ulsion
    0.72
    ety
    0.71
    Activations Density 0.018%

    No Known Activations