© 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. 7455
    Prev
    Next
    INDEX
    Explanations

    pictures or images

    oai_token-act-pair · gpt-3.5-turbo

    photos or images related to people or personal experiences

    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
    ItemTracker
    -0.85
    WAYS
    -0.77
    Few
    -0.76
    Topic
    -0.75
    istries
    -0.75
    wcs
    -0.75
    few
    -0.72
    vor
    -0.70
    rss
    -0.70
    ãĤ¦ãĤ¹
    -0.69
    POSITIVE LOGITS
     flowers
    1.00
     naked
    0.96
     smiling
    0.94
     kittens
    0.92
     oneself
    0.90
     him
    0.88
     himself
    0.84
    tnc
    0.84
     herself
    0.83
     themselves
    0.83
    Activations Density 0.153%

    No Known Activations