© 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. 9-RES-JB
    11. 18437
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues, including employment, healthcare, housing, and societal struggles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intentions, purpose, or motivations behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -1.01
     Canary
    -0.68
    calling
    -0.67
     Sparks
    -0.63
    warning
    -0.63
    hot
    -0.63
    dropping
    -0.62
     announcing
    -0.62
     delet
    -0.62
     Method
    -0.62
    POSITIVE LOGITS
     survive
    1.46
     thrive
    1.43
     consume
    1.37
     participate
    1.34
     communicate
    1.32
     fulfill
    1.31
     pursue
    1.30
     compete
    1.30
     partake
    1.30
     achieve
    1.30
    Activations Density 0.335%

    No Known Activations