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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 7943
    Prev
    Next
    INDEX
    Explanations

    people's names along with interactions like interviewing, catching up, talking to, and speaking with them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of conversations or interactions with various individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.91
    )</
    -0.72
    Jesus
    -0.63
    Definition
    -0.62
     Appears
    -0.61
    edes
    -0.60
    inventoryQuantity
    -0.60
    2020
    -0.59
    ('
    -0.59
    Interstitial
    -0.59
    POSITIVE LOGITS
     HuffPost
    0.85
     Goodman
    0.82
     VICE
    0.77
     Greenberg
    0.75
     Greenwald
    0.74
     Horowitz
    0.72
     Savage
    0.71
    VICE
    0.71
     interview
    0.70
     Torrent
    0.69
    Activations Density 0.291%

    No Known Activations