© 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. 9-RES-JB
    11. 4328
    Prev
    Next
    INDEX
    Explanations

    short phrases or phrases in dialogue that are emotionally charged or impactful

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.87
    escription
    -0.84
    aker
    -0.73
    æ©
    -0.73
    avorite
    -0.73
    bledon
    -0.70
    eatures
    -0.69
    amsung
    -0.67
    inement
    -0.66
    onial
    -0.64
    POSITIVE LOGITS
     Yeah
    1.53
     Alright
    1.50
     Hmm
    1.35
     Okay
    1.28
    Yeah
    1.27
     Oh
    1.26
     Exactly
    1.22
     Huh
    1.20
     Yep
    1.15
     Nope
    1.12
    Activations Density 0.105%

    No Known Activations