© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4303
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "tered"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "filter," particularly in contexts related to restrictions or limitations

    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
    ANA
    -0.69
    hold
    -0.68
    Solution
    -0.64
    RF
    -0.63
     suppose
    -0.63
    CLUS
    -0.62
    valid
    -0.61
    ETF
    -0.60
     largeDownload
    -0.60
     held
    -0.60
    POSITIVE LOGITS
    tered
    1.27
    tering
    1.13
    culosis
    0.89
    iated
    0.86
    onite
    0.76
    bling
    0.76
     Klux
    0.76
     tradem
    0.75
    avascript
    0.75
    ters
    0.73
    Activations Density 0.015%

    No Known Activations