© 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
    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. 7415
    Prev
    Next
    INDEX
    Explanations

    the phrase "we are" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    repetitive affirmations of existence or state of being

    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
    osate
    -0.71
    ð
    -0.67
    pedia
    -0.66
    leck
    -0.66
    rarily
    -0.65
    rouse
    -0.64
    udeau
    -0.63
    ossom
    -0.63
    Rank
    -0.61
     topple
    -0.60
    POSITIVE LOGITS
    nt
    1.00
     hereby
    1.00
     obligated
    0.95
     supposed
    0.94
     not
    0.92
    senal
    0.88
     intimately
    0.86
     gonna
    0.85
     going
    0.85
     owed
    0.84
    Activations Density 0.272%

    No Known Activations