© 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. 1-RES-JB
    6. 11465
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cry" at different intensities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cry" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nomine
    -0.71
    icient
    -0.71
    committee
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.67
    eties
    -0.66
     Roosevelt
    -0.66
    -------------
    -0.65
    ugal
    -0.64
    iciency
    -0.64
    UK
    -0.63
    POSITIVE LOGITS
     cry
    1.22
    stals
    1.15
    pter
    1.03
    baby
    0.95
    Cry
    0.92
    cry
    0.90
     Cry
    0.89
    sis
    0.84
    brate
    0.79
    hovah
    0.78
    Activations Density 0.005%

    No Known Activations