© 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. 6866
    Prev
    Next
    INDEX
    Explanations

    mentions of social media accounts

    oai_token-act-pair · gpt-3.5-turbo

    repeated or emphasized elements, indicating strong sentiments or ideas

    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
    etheless
    -0.77
     Borg
    -0.65
    hene
    -0.65
    umen
    -0.64
     sects
    -0.64
    warts
    -0.63
     HSBC
    -0.63
    leans
    -0.63
    ignty
    -0.63
     Aless
    -0.62
    POSITIVE LOGITS
    Background
    0.93
    Description
    0.87
    Reward
    0.81
    pmwiki
    0.79
    Kick
    0.78
    GROUND
    0.76
    Stretch
    0.75
    Introduction
    0.75
    ItemImage
    0.75
    Hello
    0.74
    Activations Density 0.086%

    No Known Activations