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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17513
    Prev
    Next
    INDEX
    Explanations

    the symbols 'Ļ' and 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circulation
    -0.66
     intercepted
    -0.66
     litter
    -0.65
     scattering
    -0.63
     Palestin
    -0.62
     captives
    -0.61
     dossier
    -0.60
     retrieval
    -0.60
     thwarted
    -0.60
     looms
    -0.60
    POSITIVE LOGITS
    ï¸ı
    1.39
    ï¸
    1.06
    ¯
    0.86
    laughs
    0.85
    Balt
    0.83
    âĶĢâĶĢâĶĢâĶĢ
    0.80
    âĶĢ
    0.80
    ðŁĺ
    0.79
    âĶĢâĶĢ
    0.79
    âĹ
    0.79
    Activations Density 0.659%

    No Known Activations