© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7776
    Prev
    Next
    INDEX
    Explanations

    social media handles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media handles and usernames

    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
     Scheme
    -0.91
     Ninth
    -0.90
     Policy
    -0.84
     Sale
    -0.83
     Warrant
    -0.83
     Association
    -0.82
     Advisory
    -0.82
     Parish
    -0.82
     Release
    -0.82
     Enforcement
    -0.81
    POSITIVE LOGITS
    _
    1.19
    pod
    1.11
    politics
    1.11
    podcast
    1.10
    obal
    1.06
    music
    1.01
    project
    1.00
    brown
    0.98
    football
    0.97
    gamer
    0.97
    Activations Density 0.127%

    No Known Activations