© 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 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. 17035
    Prev
    Next
    INDEX
    Explanations

    words related to "mal" or "maladies"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to malfunctions or negative characteristics of entities

    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
    VERTISEMENT
    -0.77
    ĩ
    -0.75
    ERC
    -0.70
    lio
    -0.69
     SERV
    -0.66
    á½
    -0.65
    Newsletter
    -0.65
    å§
    -0.64
     Scion
    -0.63
    onen
    -0.62
    POSITIVE LOGITS
    colm
    1.06
    icious
    0.94
    mal
    0.93
    ware
    0.89
     Nadu
    0.89
    arial
    0.88
    ignant
    0.85
    querade
    0.82
    acia
    0.81
     Lumpur
    0.80
    Activations Density 0.011%

    No Known Activations