© 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. 22291
    Prev
    Next
    INDEX
    Explanations

    names, specifically last names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Aren" 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
     srfAttach
    -0.69
     Accuracy
    -0.65
     jerk
    -0.61
     Staten
    -0.57
     extent
    -0.57
    achusetts
    -0.57
     modesty
    -0.57
    err
    -0.56
    MT
    -0.54
     Hole
    -0.53
    POSITIVE LOGITS
    emies
    0.89
    ski
    0.86
    swer
    0.83
    thal
    0.80
    thro
    0.79
    stant
    0.78
    ites
    0.78
    ko
    0.77
    heit
    0.76
    aii
    0.75
    Activations Density 0.007%

    No Known Activations