© 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. 10-RES-JB
    11. 17405
    Prev
    Next
    INDEX
    Explanations

    special characters, likely non-standard line breaks

    oai_token-act-pair · gpt-3.5-turbo

    instances of urgency or critical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     citiz
    -0.80
     footing
    -0.75
    naissance
    -0.71
    cius
    -0.68
     undermin
    -0.67
    ¥ŀ
    -0.63
    hement
    -0.62
    aditional
    -0.61
     exha
    -0.60
    etheless
    -0.60
    POSITIVE LOGITS
    Eventually
    1.09
    Then
    1.00
    Later
    0.99
    ³³³³
    0.97
    ³³³³³³³³
    0.92
    DragonMagazine
    0.89
    Bus
    0.85
    Suddenly
    0.85
    ³³³
    0.85
    Scroll
    0.84
    Activations Density 0.412%

    No Known Activations