© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1043
    Prev
    Next
    INDEX
    Explanations

    emotions or internal states related to the heart or mind

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional or metaphorical concepts related to hearts and minds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onomy
    -0.68
    ression
    -0.66
     communism
    -0.66
    ressive
    -0.63
     heterogeneity
    -0.60
    ECH
    -0.60
     avoidance
    -0.58
    treatment
    -0.58
     withdrawal
    -0.57
    Recomm
    -0.57
    POSITIVE LOGITS
    paces
    1.58
    chool
    1.50
    pace
    1.45
    creen
    1.38
    mith
    1.34
    pring
    1.30
    hare
    1.27
    peed
    1.23
    poons
    1.21
    hips
    1.21
    Activations Density 0.244%

    No Known Activations