© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11144
    Prev
    Next
    INDEX
    Explanations

    words related to dependency and reliance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dependence and dependency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izers
    -0.76
    mberg
    -0.73
    izer
    -0.71
    isers
    -0.69
    \\\\\\\\
    -0.68
    efer
    -0.68
    ²¾
    -0.66
    awar
    -0.66
    ning
    -0.66
    ventory
    -0.65
    POSITIVE LOGITS
    encies
    1.16
     upon
    1.10
    ency
    0.98
     orig
    0.84
     Upon
    0.79
    ently
    0.76
    cipline
    0.74
    enance
    0.72
     dependency
    0.72
    onial
    0.70
    Activations Density 0.036%

    No Known Activations