© 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. 13636
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative occurrences or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific situations or incidents

    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
    eers
    -0.70
    ensibly
    -0.70
    eer
    -0.65
    omers
    -0.63
    istries
    -0.62
    well
    -0.60
    rote
    -0.59
    anwhile
    -0.58
    reath
    -0.58
    ãĥı
    -0.57
    POSITIVE LOGITS
    tical
    0.80
     anymore
    0.73
     happening
    0.68
     trope
    0.68
    tics
    0.67
    tic
    0.67
    ï¸ı
    0.66
    riber
    0.66
     existed
    0.64
    Untitled
    0.63
    Activations Density 0.064%

    No Known Activations