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. 1-RES-JB
    6. 7719
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "marsh" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "marsh" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.71
    aughs
    -0.64
     Essential
    -0.63
     tense
    -0.61
     unheard
    -0.59
     superficial
    -0.59
     deaf
    -0.58
     Belt
    -0.58
     human
    -0.57
    Tip
    -0.57
    POSITIVE LOGITS
    mallow
    1.62
     marsh
    1.44
    alled
    1.09
     Marshal
    1.06
    ãĤ©
    0.99
    alling
    0.99
    Marsh
    0.90
    als
    0.90
    aling
    0.87
    aled
    0.86
    Activations Density 0.003%

    No Known Activations