Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4611
    Prev
    Next
    INDEX
    Explanations

    social media platform names

    oai_token-act-pair · gpt-3.5-turbo

    references to Facebook and its associated services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -0.94
    lass
    -0.75
    heny
    -0.74
    ved
    -0.74
    rer
    -0.74
    ptin
    -0.73
    DERR
    -0.72
    cised
    -0.68
    zin
    -0.67
     externalToEVAOnly
    -0.67
    POSITIVE LOGITS
     Messenger
    1.06
    nect
    1.00
     Live
    0.90
     Pages
    0.85
     Likes
    0.81
    username
    0.81
     Timeline
    0.74
     Ads
    0.74
    osphere
    0.74
     Gifts
    0.73
    Activations Density 0.047%

    No Known Activations