© 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. 10-RES-JB
    11. 16693
    Prev
    Next
    INDEX
    Explanations

    social media links prompting to follow accounts

    oai_token-act-pair · gpt-3.5-turbo

    instances of social media follow requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minist
    -0.75
    pite
    -0.73
     ILCS
    -0.67
    wagen
    -0.63
     lob
    -0.59
     halluc
    -0.59
    endiary
    -0.58
    ãĥ¯ãĥ³
    -0.58
     coron
    -0.58
     nerv
    -0.57
    POSITIVE LOGITS
     @
    1.03
     HuffPost
    0.89
     Stories
    0.88
    ers
    0.87
     us
    0.85
    ership
    0.84
     Us
    0.81
    ed
    0.77
     VICE
    0.75
     me
    0.74
    Activations Density 0.018%

    No Known Activations