© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11722
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, possibly related to formatting or encoding errors

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-standard symbols

    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
     exha
    -0.87
     mathemat
    -0.79
     contrace
    -0.77
     answ
    -0.76
    geries
    -0.74
     dossier
    -0.73
     unborn
    -0.70
     Citiz
    -0.69
     unfinished
    -0.68
     misunder
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.85
    ï¸
    1.37
    âĸł
    1.09
    âĿ
    1.05
    â
    1.02
    ðŁ
    0.99
    âĸº
    0.99
    âĻ¦
    0.99
    âĪ
    0.98
    âķIJâķIJ
    0.97
    Activations Density 0.065%

    No Known Activations