© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11177
    Prev
    Next
    INDEX
    Explanations

    instances of the word "tank."

    oai_token-act-pair · gpt-3.5-turbo

    references to tanks

    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
    âĸ¬
    -0.92
    BOOK
    -0.72
    ————
    -0.68
    teness
    -0.67
    phony
    -0.67
    ãĥ¬
    -0.66
     Brotherhood
    -0.65
    theless
    -0.65
     Lod
    -0.65
    çīĪ
    -0.65
    POSITIVE LOGITS
    erness
    1.22
    ard
    1.00
    mates
    0.99
    ards
    0.99
    ered
    0.94
    yard
    0.94
    agers
    0.93
    tank
    0.91
    ering
    0.90
    tops
    0.85
    Activations Density 0.040%

    No Known Activations