© 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. 3-RES-JB
    11. 20097
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mal" with various endings

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mal" or related to it, likely indicating a focus on the subject of Malian contexts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.74
    å§
    -0.74
     NETWORK
    -0.71
    arettes
    -0.69
     Citation
    -0.69
    ICLE
    -0.69
    ALK
    -0.68
    ITED
    -0.68
     Carbuncle
    -0.66
     FACE
    -0.65
    POSITIVE LOGITS
    icious
    1.03
    ignant
    1.00
    colm
    0.98
    adies
    0.97
    practice
    0.97
    ady
    0.92
    ibu
    0.92
    vin
    0.89
    mort
    0.89
    acca
    0.89
    Activations Density 0.011%

    No Known Activations