© 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. 2-RES-JB
    11. 13796
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific character, possibly from a book or movie, that seems to have a protective or consuming nature

    oai_token-act-pair · gpt-3.5-turbo

    proper names, specifically those related to individuals and their roles or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     2600
    -0.78
    ITNESS
    -0.77
     AVG
    -0.72
    Interstitial
    -0.69
     Holmes
    -0.69
     Corpus
    -0.66
     1886
    -0.66
    ALS
    -0.65
     Berkshire
    -0.65
    çĽ
    -0.65
    POSITIVE LOGITS
     Drag
    1.17
    Drag
    0.99
    glers
    0.97
    ón
    0.94
    oon
    0.94
    hett
    0.93
    achel
    0.88
    ged
    0.88
    otten
    0.87
    assi
    0.87
    Activations Density 0.007%

    No Known Activations