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. 1339
    Prev
    Next
    INDEX
    Explanations

    the word "anche" with strong activation values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of words that include the suffix "anche."

    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
    ODUCT
    -0.66
    APS
    -0.65
     atmospheric
    -0.63
     alarming
    -0.60
    ITE
    -0.59
     intimidating
    -0.59
    olved
    -0.59
     exponential
    -0.58
    OD
    -0.57
     disparate
    -0.56
    POSITIVE LOGITS
    anche
    1.33
    eers
    1.08
    ttes
    0.91
    erness
    0.89
    xia
    0.81
    tta
    0.80
    sburg
    0.78
    wright
    0.78
    anches
    0.77
    eering
    0.77
    Activations Density 0.006%

    No Known Activations