© 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. 10-RES-JB
    11. 3047
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of understanding or desire for accountability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ľ"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     targeted
    -0.86
     pigeon
    -0.83
     clitor
    -0.80
     pyramid
    -0.75
     tyres
    -0.72
     relative
    -0.72
     envelope
    -0.70
     eyeb
    -0.70
     favor
    -0.70
     favour
    -0.69
    POSITIVE LOGITS
    ï¸ı
    1.45
    ï¸
    1.06
    However
    1.05
    Therefore
    1.01
    ICE
    0.97
    Roberts
    0.97
    âĶĢâĶĢâĶĢâĶĢ
    0.97
    RELATED
    0.97
    Unfortunately
    0.96
    Likewise
    0.94
    Activations Density 0.145%

    No Known Activations