© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    positive or negative sentiments towards various aspects like poems, stories, and movies

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal enjoyment and appreciation of art

    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
    abama
    -0.65
     respectively
    -0.65
    ebus
    -0.64
    aukee
    -0.63
    angering
    -0.63
    iances
    -0.62
    rees
    -0.62
    devices
    -0.62
    cipled
    -0.60
    aneers
    -0.60
    POSITIVE LOGITS
     its
    1.35
    Its
    1.33
     Its
    1.30
     it
    1.24
     my
    1.04
     myself
    1.03
     I
    0.97
     ITS
    0.95
    its
    0.85
     It
    0.84
    Activations Density 0.643%

    No Known Activations