© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15494
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences ending with the word "how"

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "how"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereafter
    -0.65
    izu
    -0.64
     ........
    -0.61
    astical
    -0.59
     nib
    -0.59
    availability
    -0.58
    uthor
    -0.56
    comings
    -0.56
     yak
    -0.56
     Skydragon
    -0.56
    POSITIVE LOGITS
    HCR
    0.79
    soever
    0.77
    beit
    0.74
    bill
    0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.69
    ever
    0.67
    ls
    0.67
     much
    0.65
    jriwal
    0.63
    vier
    0.63
    Activations Density 0.034%

    No Known Activations