© 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. 16305
    Prev
    Next
    INDEX
    Explanations

    names of specific people, particularly 'Heather'

    oai_token-act-pair · gpt-3.5-turbo

    names, particularly those of individuals mentioned in various contexts

    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
    ozy
    -0.76
    577
    -0.73
     unsub
    -0.72
    uador
    -0.72
    geon
    -0.70
    SPONSORED
    -0.69
    Stars
    -0.69
    awaru
    -0.69
    hibition
    -0.69
    ocre
    -0.68
    POSITIVE LOGITS
     Loren
    0.96
    rette
    0.93
    ottesville
    0.91
    rike
    0.82
    sburg
    0.78
    rons
    0.78
     Heather
    0.78
    ewater
    0.76
     Joy
    0.75
    aith
    0.74
    Activations Density 0.011%

    No Known Activations