© 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. 3-RES-JB
    11. 116
    Prev
    Next
    INDEX
    Explanations

    references to the term "sharia"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "sh"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.77
     Ajax
    -0.76
    OLOGY
    -0.75
     Reach
    -0.72
    PsyNetMessage
    -0.72
     Leth
    -0.70
     Sacrament
    -0.69
     è£ıè
    -0.68
    DragonMagazine
    -0.67
    anwhile
    -0.65
    POSITIVE LOGITS
    atters
    1.21
    apesh
    1.14
    uff
    1.12
    ippers
    1.11
    ooting
    1.11
    ivering
    1.09
    ipped
    1.08
    aded
    1.07
    ipping
    1.06
    attering
    1.06
    Activations Density 0.011%

    No Known Activations