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. 3-RES-JB
    6. 10180
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bank"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ank" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perature
    -0.71
     skelet
    -0.69
     sclerosis
    -0.67
     isot
    -0.67
     guiIcon
    -0.66
     withd
    -0.66
     fibers
    -0.65
     Beir
    -0.65
     antigen
    -0.62
     redistributed
    -0.62
    POSITIVE LOGITS
    ank
    1.01
    enstein
    0.90
    ernel
    0.88
    er
    0.87
    erous
    0.84
    owski
    0.84
    uild
    0.83
    furt
    0.81
    iewicz
    0.80
    aly
    0.79
    Activations Density 0.008%

    No Known Activations