© 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. 2-RES-JB
    11. 7653
    Prev
    Next
    INDEX
    Explanations

    words related to poor quality or negative assessment

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to poor quality or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrut
    -0.88
    Topics
    -0.86
    sen
    -0.85
    isman
    -0.82
    lean
    -0.79
    encers
    -0.77
    iferation
    -0.76
    omen
    -0.76
    hip
    -0.75
    ophon
    -0.75
    POSITIVE LOGITS
     crappy
    0.91
     Bastard
    0.83
     shitty
    0.80
     bye
    0.77
     bung
    0.77
     asses
    0.74
     rotten
    0.73
     darn
    0.72
     quality
    0.70
     bastard
    0.70
    Activations Density 0.015%

    No Known Activations