© 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. 17896
    Prev
    Next
    INDEX
    Explanations

    references to the online platform "4chan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of online communities, specifically 4chan and its related threads

    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
    ences
    -0.79
    ENC
    -0.72
     Ferr
    -0.65
     Luxem
    -0.63
     Vaugh
    -0.63
     Disp
    -0.62
    enced
    -0.61
    ourcing
    -0.59
     Jarrett
    -0.59
     Mandela
    -0.59
    POSITIVE LOGITS
    chan
    1.08
    nel
    0.97
    esthetic
    0.97
    nels
    0.92
    elist
    0.91
    esthesia
    0.91
    icum
    0.84
    ovic
    0.83
    azi
    0.81
    thur
    0.81
    Activations Density 0.046%

    No Known Activations