© 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. 11-RES-JB
    11. 7581
    Prev
    Next
    INDEX
    Explanations

    positive expressions and sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of admiration and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erenn
    -0.80
    soever
    -0.73
    uria
    -0.65
    bable
    -0.64
    agues
    -0.63
    Else
    -0.61
    CENT
    -0.60
    istance
    -0.59
     operative
    -0.59
     predicate
    -0.59
    POSITIVE LOGITS
     how
    1.85
    how
    1.38
     HOW
    1.12
     why
    1.02
     How
    0.98
     what
    0.90
    HOW
    0.81
    How
    0.76
     seeing
    0.75
     whether
    0.75
    Activations Density 0.467%

    No Known Activations