© 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. 2-RES-JB
    11. 18810
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "fixed" or "fixed amount"

    oai_token-act-pair · gpt-3.5-turbo

    references to fixed quantities or limits

    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
    anasia
    -1.02
    ynthesis
    -0.84
    arenthood
    -0.79
    esis
    -0.78
    ivals
    -0.77
    alogy
    -0.76
    udi
    -0.72
    anqu
    -0.72
    çĶŁ
    -0.68
     GOODMAN
    -0.68
    POSITIVE LOGITS
    fixed
    1.08
     fixed
    1.02
     Fixed
    0.83
     fix
    0.81
    fix
    0.78
     satisf
    0.69
     fixing
    0.69
    lear
    0.67
    ĵĺ
    0.66
    FIX
    0.65
    Activations Density 0.011%

    No Known Activations