© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11577
    Prev
    Next
    INDEX
    Explanations

    texts related to criticism and pointing out flaws

    oai_token-act-pair · gpt-3.5-turbo

    terms related to imperfections or weaknesses

    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
    rooms
    -0.74
    NAS
    -0.73
    cer
    -0.72
    zee
    -0.70
    unin
    -0.69
    xon
    -0.67
    room
    -0.65
    xa
    -0.64
    idal
    -0.63
    uclear
    -0.62
    POSITIVE LOGITS
     flaws
    1.39
     flaw
    1.11
     weaknesses
    1.01
     faults
    1.01
     shortcomings
    0.97
     compromises
    0.93
     plag
    0.92
     vulnerabilities
    0.83
    acies
    0.83
     guiActiveUn
    0.80
    Activations Density 0.016%

    No Known Activations