© 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. 7230
    Prev
    Next
    INDEX
    Explanations

    words related to ships and ship-related activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ships

    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
    âĶģ
    -0.90
    çīĪ
    -0.81
    osate
    -0.66
    ALLY
    -0.66
    aneously
    -0.66
    okers
    -0.64
     confir
    -0.63
    theless
    -0.62
     Marketable
    -0.62
     Aven
    -0.61
    POSITIVE LOGITS
    wreck
    1.88
    yard
    1.45
    yards
    1.34
    wright
    1.30
    building
    1.19
    builder
    1.17
    shape
    1.13
    builders
    1.11
    mates
    1.07
     Graveyard
    1.00
    Activations Density 0.036%

    No Known Activations