© 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. 2-RES-JB
    11. 19800
    Prev
    Next
    INDEX
    Explanations

    phrases related to cold temperature or relaxation

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "chill" and related concepts of relaxation or coldness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PART
    -0.81
    ragon
    -0.81
    lder
    -0.78
    ĻĤ
    -0.77
    prises
    -0.74
    DES
    -0.73
    uers
    -0.70
    ================================
    -0.69
    ged
    -0.69
    rights
    -0.68
    POSITIVE LOGITS
     Chill
    1.12
     chill
    0.98
    ingly
    0.89
     cooker
    0.81
    iness
    0.79
    ings
    0.77
    iw
    0.77
    iflower
    0.76
    warm
    0.74
    achine
    0.74
    Activations Density 0.007%

    No Known Activations