© 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. 8-RES-JB
    11. 7841
    Prev
    Next
    INDEX
    Explanations

    words indicating a shift or change in a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes in status or transformation over time

    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
    LOCK
    -0.67
    LLOW
    -0.64
     purse
    -0.58
     worthy
    -0.57
    MC
    -0.56
     deserve
    -0.55
     bodily
    -0.55
    Champ
    -0.53
     Logged
    -0.53
     Sik
    -0.53
    POSITIVE LOGITS
    uddenly
    1.01
     suddenly
    0.84
    today
    0.75
    iott
    0.74
    apult
    0.72
    instead
    0.69
    emer
    0.69
     reversed
    0.69
    artney
    0.68
    nox
    0.67
    Activations Density 0.624%

    No Known Activations