© 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. 10-RES-JB
    11. 7824
    Prev
    Next
    INDEX
    Explanations

    company or brand names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific companies or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discredited
    -0.81
     presumably
    -0.77
     nonexistent
    -0.76
     misdem
    -0.75
     doubtful
    -0.74
     exacerbated
    -0.73
     irrelevant
    -0.73
     insin
    -0.73
     pretext
    -0.73
     inciting
    -0.72
    POSITIVE LOGITS
    topia
    0.87
    duino
    0.81
     Bottle
    0.75
    Sphere
    0.75
    opia
    0.74
    Spring
    0.74
     Harvest
    0.74
     Designs
    0.74
    Haunted
    0.73
    Gro
    0.73
    Activations Density 0.717%

    No Known Activations