© 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. 10332
    Prev
    Next
    INDEX
    Explanations

    words related to outdated or old-fashioned things

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ated" in various contexts

    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
    alter
    -0.76
    Lean
    -0.70
    hold
    -0.70
    LOD
    -0.68
    lua
    -0.68
    FTWARE
    -0.67
    issues
    -0.67
    PER
    -0.65
    MA
    -0.65
    MET
    -0.64
    POSITIVE LOGITS
    ated
    0.97
    ating
    0.85
    htaking
    0.83
    uated
    0.83
    anamo
    0.78
    ĵĺ
    0.75
     destro
    0.75
    ivating
    0.74
    phabet
    0.72
    urally
    0.71
    Activations Density 0.035%

    No Known Activations