© 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. 8495
    Prev
    Next
    INDEX
    Explanations

    specific programming terms, such as software languages and tools

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and technical terms related to specific software or 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
    ãĥ£
    -0.74
    pired
    -0.72
    uminati
    -0.68
    thens
    -0.65
    ointed
    -0.64
     ðŁij
    -0.64
    -0.62
    docker
    -0.61
    âĢİ
    -0.61
     infographic
    -0.60
    POSITIVE LOGITS
     itself
    1.06
    +.
    0.85
     herself
    0.83
     himself
    0.82
    topia
    0.77
     Ventures
    0.77
    +,
    0.75
    MSN
    0.74
    speak
    0.73
    HQ
    0.72
    Activations Density 0.374%

    No Known Activations