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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 9097
    Prev
    Next
    INDEX
    Explanations

    words related to military vessels, specifically the term "Cru"ца

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "Cruiser" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Referred
    -0.69
    è¦ļéĨĴ
    -0.66
     McCabe
    -0.66
    nah
    -0.62
    BACK
    -0.61
     Stard
    -0.61
    raised
    -0.61
    upon
    -0.59
     Lomb
    -0.59
    IONS
    -0.58
    POSITIVE LOGITS
    isers
    1.47
    cible
    1.39
    cially
    1.38
    ciating
    1.36
    cial
    1.33
    isin
    1.29
    ises
    1.25
    ising
    1.24
    iser
    1.19
    ised
    1.08
    Activations Density 0.033%

    No Known Activations