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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 6-RES-JB
    6. 10200
    Prev
    Next
    INDEX
    Explanations

    phrases containing non-alphanumeric characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "it is" or similar phrases indicating statements or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funer
    -0.77
     Annotations
    -0.74
     Nib
    -0.68
     scattering
    -0.66
     warnings
    -0.66
     Rag
    -0.64
     guiActiveUnfocused
    -0.64
     Detail
    -0.64
     vomiting
    -0.62
     Tanz
    -0.62
    POSITIVE LOGITS
    should
    0.88
    erest
    0.87
    pires
    0.87
    tains
    0.86
    §
    0.85
    ¯
    0.82
    agree
    0.81
    º
    0.80
    Ĵ
    0.80
    ates
    0.79
    Activations Density 0.172%

    No Known Activations