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. 7-RES-JB
    6. 6861
    Prev
    Next
    INDEX
    Explanations

    lobster-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lobsters and crabs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Constructed
    -0.80
     CHRIST
    -0.71
     Archangel
    -0.71
     Valhalla
    -0.68
    OAD
    -0.65
    Male
    -0.64
     Trance
    -0.63
    ++++
    -0.63
     Angel
    -0.62
     IST
    -0.62
    POSITIVE LOGITS
    otom
    1.64
    bing
    1.45
    otomy
    1.45
    bed
    1.24
    bons
    1.07
    bers
    1.07
    tailed
    1.03
    sters
    1.03
    elia
    1.02
    rolet
    1.00
    Activations Density 0.048%

    No Known Activations