© 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. 14079
    Prev
    Next
    INDEX
    Explanations

    content meant for sharing on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sharing content

    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
    vernment
    -0.71
     includ
    -0.67
    rift
    -0.64
     desper
    -0.63
     awa
    -0.61
    pora
    -0.60
     cradle
    -0.60
     ushered
    -0.59
    ailability
    -0.59
    rail
    -0.58
    POSITIVE LOGITS
     Helpful
    0.69
     Below
    0.67
     Related
    0.67
    Article
    0.66
     PsyNet
    0.65
    iframe
    0.64
     Shares
    0.64
     Story
    0.64
     Email
    0.64
     Share
    0.62
    Activations Density 0.010%

    No Known Activations