© 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. 10599
    Prev
    Next
    INDEX
    Explanations

    names of people or entities followed by a colon

    oai_token-act-pair · gpt-3.5-turbo

    colons as indicators of speaker transitions

    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
    inement
    -0.74
     overl
    -0.67
     staged
    -0.63
     decorations
    -0.63
     troubles
    -0.63
    sburg
    -0.63
     targeted
    -0.62
     pursu
    -0.62
    pins
    -0.62
     flock
    -0.60
    POSITIVE LOGITS
     Yeah
    1.21
     Alright
    1.10
     Hmm
    1.01
     Okay
    0.97
     Exactly
    0.96
     Huh
    0.95
    Yeah
    0.93
     Absolutely
    0.93
     Firstly
    0.93
     Hey
    0.93
    Activations Density 0.077%

    No Known Activations