Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12045
    Prev
    Next
    INDEX
    Explanations

    words related to a specific object: "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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.94
    theless
    -0.72
    BOOK
    -0.70
    ————
    -0.67
     DMCA
    -0.67
     Brotherhood
    -0.67
    teness
    -0.64
    éĹ
    -0.64
    女
    -0.63
     Lod
    -0.63
    POSITIVE LOGITS
    erness
    1.14
    ards
    1.03
    mates
    0.98
    yard
    0.96
    ard
    0.96
    tank
    0.93
    agers
    0.93
    pit
    0.88
    ered
    0.87
    buster
    0.87
    Activations Density 0.034%

    No Known Activations