© 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. 10-RES-JB
    11. 3162
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different physical and emotional states or activities of a person

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional intensity or strong feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attRot
    -0.66
    Methods
    -0.65
    azard
    -0.65
    selves
    -0.64
     unison
    -0.64
    arser
    -0.61
     respectively
    -0.61
    TPS
    -0.58
    their
    -0.58
     jointly
    -0.57
    POSITIVE LOGITS
     himself
    1.33
     Himself
    1.10
     herself
    1.08
     his
    1.03
     tonight
    0.93
     His
    0.93
     HIS
    0.93
    his
    0.87
    His
    0.86
     Wife
    0.78
    Activations Density 0.791%

    No Known Activations