© 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. 11-RES-JB
    11. 1870
    Prev
    Next
    INDEX
    Explanations

    instances of weapons or threats involving them

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faces
    -0.80
    facts
    -0.80
     alliances
    -0.78
    names
    -0.77
    attacks
    -0.76
    ees
    -0.75
    Events
    -0.75
    grounds
    -0.74
    oids
    -0.74
    artifacts
    -0.74
    POSITIVE LOGITS
     clipboard
    1.14
     handgun
    1.12
     towel
    1.11
     cane
    1.10
     flashlight
    1.10
     suitcase
    1.08
     broom
    1.05
     revolver
    1.03
     backpack
    1.02
     knife
    1.02
    Activations Density 0.165%

    No Known Activations