© 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. 4-RES-JB
    6. 7445
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or observations

    oai_token-act-pair · gpt-3.5-turbo

    the use of specific pronouns and demonstrative words

    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
     ..."
    -0.69
    .","
    -0.65
     �
    -0.59
     \"
    -0.59
    \"
    -0.55
    .</
    -0.54
     ...
    -0.53
     respectively
    -0.51
     ``(
    -0.50
     â̦"
    -0.49
    POSITIVE LOGITS
    odore
    1.01
    resa
    0.95
    xiety
    0.83
    notations
    0.79
    bidden
    0.75
    ibliography
    0.75
    foundland
    0.72
    swers
    0.71
    withstanding
    0.71
    tymology
    0.71
    Activations Density 0.803%

    No Known Activations