© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14386
    Prev
    Next
    INDEX
    Explanations

    terms related to various crimes like theft and robbery

    oai_token-act-pair · gpt-3.5-turbo

    references to specific identifiers or titles within a variety of contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    æ©
    -0.72
    ¿½
    -0.70
    PsyNetMessage
    -0.66
    URA
    -0.65
    GBT
    -0.63
    ĨĴ
    -0.61
    iterranean
    -0.60
    ensical
    -0.60
    wikipedia
    -0.58
    ña
    -0.58
    POSITIVE LOGITS
    ittens
    0.69
    rosis
    0.67
    ®
    0.66
     Tactics
    0.65
     Melee
    0.62
     Removal
    0.62
    mania
    0.62
    âĦ¢
    0.60
     Unlimited
    0.59
    Mania
    0.59
    Activations Density 0.884%

    No Known Activations