© 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. 8-RES-JB
    11. 3150
    Prev
    Next
    INDEX
    Explanations

    instances of non-alphabetic characters in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the character or symbol "Ļ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prolifer
    -0.80
     elim
    -0.77
     mathemat
    -0.77
     contrace
    -0.73
     disadvant
    -0.72
     misunder
    -0.71
     sacrific
    -0.70
     fortun
    -0.70
     loopholes
    -0.68
     multiplying
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.50
    ski
    1.12
    tre
    0.98
    sky
    0.96
    daughter
    0.91
    bart
    0.90
    hoe
    0.90
    Jr
    0.87
    son
    0.86
    minent
    0.85
    Activations Density 0.162%

    No Known Activations