© 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. 3530
    Prev
    Next
    INDEX
    Explanations

    instances of the word "unfortunately"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of regret or disappointment

    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
    ingham
    -0.84
    enders
    -0.77
    tein
    -0.74
    mails
    -0.74
    mail
    -0.74
    fect
    -0.72
    lee
    -0.71
    lets
    -0.70
    venant
    -0.70
    agers
    -0.69
    POSITIVE LOGITS
     sadly
    0.97
     unfortunately
    0.92
     regrett
    0.85
    ा
    0.79
     conflic
    0.74
    Ń·
    0.74
     mosqu
    0.72
     parted
    0.70
     dear
    0.70
     tragically
    0.69
    Activations Density 0.008%

    No Known Activations