© 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. 10404
    Prev
    Next
    INDEX
    Explanations

    instances of the word "miss" followed by a number indicating the strength of the match

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "miss"

    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
    EStreamFrame
    -0.79
    iltration
    -0.78
    cius
    -0.70
    Enlarge
    -0.68
    RAW
    -0.67
    itutional
    -0.65
    ipel
    -0.65
     toget
    -0.64
    REDACTED
    -0.60
    doi
    -0.60
    POSITIVE LOGITS
    pelled
    1.08
     miss
    1.06
    hap
    0.96
    pell
    0.92
    ouri
    0.83
    cules
    0.83
    pelling
    0.82
    oons
    0.81
     missed
    0.79
    oon
    0.77
    Activations Density 0.006%

    No Known Activations