© 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. 14357
    Prev
    Next
    INDEX
    Explanations

    the specific term "ter" followed by a single digit number, potentially referring to storage capacity or technology measurements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ter."

    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
    orship
    -0.79
    ELS
    -0.75
    Downloadha
    -0.74
    OWS
    -0.73
    uberty
    -0.73
    odcast
    -0.72
    ":"/
    -0.72
    hetti
    -0.71
    ortium
    -0.69
    olitan
    -0.69
    POSITIVE LOGITS
    rigan
    0.98
    abytes
    0.96
    abyte
    0.88
     ter
    0.88
     lapt
    0.86
    ranean
    0.85
    cedes
    0.85
    riers
    0.83
    yll
    0.83
    bour
    0.83
    Activations Density 0.006%

    No Known Activations