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. 7-RES-JB
    6. 21911
    Prev
    Next
    INDEX
    Explanations

    the character 'ľ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ľ" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaugh
    -0.82
     manif
    -0.80
     disadvant
    -0.74
     ropes
    -0.72
     slic
    -0.71
     deed
    -0.71
     machines
    -0.70
     condem
    -0.70
     womb
    -0.70
     tides
    -0.69
    POSITIVE LOGITS
    âĶĢâĶĢ
    0.96
    ï¸ı
    0.81
    âĶĢâĶĢâĶĢâĶĢ
    0.80
     Edited
    0.79
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.79
    âĸ¬âĸ¬
    0.76
    requently
    0.75
    ----------------------------------------------------------------
    0.72
    STER
    0.72
    ---------------
    0.71
    Activations Density 0.102%

    No Known Activations