© 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. 18461
    Prev
    Next
    INDEX
    Explanations

    email addresses or usernames on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media handles

    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
     accordingly
    -0.69
     Strikes
    -0.68
     fitting
    -0.66
     Takeru
    -0.65
     hence
    -0.64
     reintrodu
    -0.63
     Pumpkin
    -0.63
     humiliating
    -0.63
     Supplemental
    -0.62
    ITION
    -0.62
    POSITIVE LOGITS
    gmail
    1.69
    yahoo
    1.45
    hot
    1.10
    debian
    1.10
    bleacher
    1.04
    earth
    1.04
    home
    1.00
    mac
    0.97
    hillary
    0.97
    domain
    0.96
    Activations Density 0.017%

    No Known Activations