© 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. 23796
    Prev
    Next
    INDEX
    Explanations

    lists of topics or content types in a document

    oai_token-act-pair · gpt-3.5-turbo

    elements of enthusiasm or positive affirmations

    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
     freel
    -0.81
     pand
    -0.79
     defund
    -0.78
     coordinated
    -0.77
     divest
    -0.77
     pupp
    -0.77
     disinformation
    -0.76
     betting
    -0.74
     causal
    -0.74
     migrant
    -0.74
    POSITIVE LOGITS
    Features
    1.60
    Product
    1.46
    Rated
    1.36
    Pros
    1.32
    Performance
    1.30
     Specifications
    1.28
    Mini
    1.23
    Motor
    1.22
    Price
    1.22
    Hardware
    1.20
    Activations Density 0.323%

    No Known Activations