© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6366
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital technology and services

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with digital content and technology

    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
    reditary
    -0.79
    ealous
    -0.67
    nen
    -0.65
     Parish
    -0.63
     Lutheran
    -0.61
     Rebell
    -0.61
    iqueness
    -0.60
    volent
    -0.59
    ModLoader
    -0.58
    icipated
    -0.58
    POSITIVE LOGITS
    rencies
    0.85
     converter
    0.77
    UGC
    0.75
    Apps
    0.72
    DragonMagazine
    0.72
    advertisement
    0.70
    Maker
    0.68
     startup
    0.68
     interface
    0.68
    devices
    0.67
    Activations Density 0.466%

    No Known Activations