© 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. 1-RES-JB
    11. 10432
    Prev
    Next
    INDEX
    Explanations

    proper nouns and adjectives related to stories, history, and physical states, especially negative ones

    oai_token-act-pair · gpt-3.5-turbo

    words that describe stories or narratives, particularly around struggles or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.77
    utonium
    -0.76
    obal
    -0.72
    inctions
    -0.72
    ovych
    -0.71
    blance
    -0.71
    ©¶æ
    -0.70
     interfered
    -0.68
    ogh
    -0.68
    peria
    -0.67
    POSITIVE LOGITS
     businesses
    0.75
    town
    0.74
     Barkley
    0.74
     Cary
    0.73
    ãĤ¤ãĥĪ
    0.72
     quaint
    0.72
     Aven
    0.71
     Springfield
    0.69
    oried
    0.68
    lehem
    0.68
    Activations Density 0.036%

    No Known Activations