© 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. 10-RES-JB
    6. 1137
    Prev
    Next
    INDEX
    Explanations

    negative and critical language

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disparagement and derogatory comments

    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
    querque
    -0.79
     Paso
    -0.64
    onics
    -0.62
    FO
    -0.61
    eland
    -0.60
    sequence
    -0.59
     LW
    -0.59
     Wonders
    -0.59
     sync
    -0.59
    changes
    -0.59
    POSITIVE LOGITS
    agement
    0.92
     vil
    0.89
    icious
    0.86
    aging
    0.85
    ately
    0.84
    rating
    0.82
     ridic
    0.80
    ified
    0.78
    ighed
    0.78
     dispar
    0.75
    Activations Density 0.063%

    No Known Activations