© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12499
    Prev
    Next
    INDEX
    Explanations

    technical or conceptual terms related to significant shifts or transformations

    oai_token-act-pair · gpt-3.5-turbo

    references to paradigms and paradigm shifts

    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
    llah
    -0.98
    hire
    -0.75
    ertodd
    -0.74
    Lago
    -0.70
    enhagen
    -0.68
    idan
    -0.67
    cffff
    -0.66
    ipedia
    -0.66
    sports
    -0.65
    ionage
    -0.65
    POSITIVE LOGITS
     paradigm
    0.93
    igmatic
    0.92
     shift
    0.85
     Shift
    0.82
     Parad
    0.80
     parad
    0.77
    igm
    0.74
    geist
    0.73
    atically
    0.71
    ually
    0.70
    Activations Density 0.054%

    No Known Activations