© 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. 6362
    Prev
    Next
    INDEX
    Explanations

    words related to slipping or sliding

    oai_token-act-pair · gpt-3.5-turbo

    variations of the sound "sl" at the start of words

    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
    OTOS
    -0.72
    ALS
    -0.68
    ENTION
    -0.62
    ACTED
    -0.61
    EA
    -0.60
    romeda
    -0.59
    ICAN
    -0.59
    erity
    -0.58
     WARN
    -0.58
     sacrifice
    -0.58
    POSITIVE LOGITS
    odan
    1.12
    ppe
    0.86
    inki
    0.82
    eways
    0.79
    tarian
    0.79
    ppy
    0.78
    akia
    0.78
    tarians
    0.78
    ando
    0.76
    eway
    0.76
    Activations Density 0.090%

    No Known Activations