© 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. 7-RES-JB
    11. 7952
    Prev
    Next
    INDEX
    Explanations

    phrases related to news events or mentions of specific locations or years

    oai_token-act-pair · gpt-3.5-turbo

    specific locations and references to time and circumstance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yond
    -0.57
    true
    -0.56
    '.
    -0.55
    $.
    -0.55
    pac
    -0.54
    Advertisements
    -0.54
    clusively
    -0.52
    soType
    -0.52
    atever
    -0.51
     Surviv
    -0.51
    POSITIVE LOGITS
     consisted
    1.05
     consists
    0.98
     seemed
    0.98
     fared
    0.95
     refers
    0.91
     seems
    0.91
     appears
    0.88
     grew
    0.87
     reacted
    0.86
     belonged
    0.86
    Activations Density 0.353%

    No Known Activations