© 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. 1-RES-JB
    6. 2364
    Prev
    Next
    INDEX
    Explanations

    phrases related to outlining or structuring information

    oai_token-act-pair · gpt-3.5-turbo

    references to outlines or structured plans

    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
    alle
    -0.73
    hib
    -0.69
    airs
    -0.69
    taboola
    -0.67
    enos
    -0.67
    jud
    -0.67
    nesia
    -0.66
    eno
    -0.66
    onte
    -0.65
    ammy
    -0.64
    POSITIVE LOGITS
     outline
    1.64
     outlines
    1.58
     outlining
    1.03
     WARN
    0.92
     synopsis
    0.83
     sket
    0.83
     sketches
    0.80
    escription
    0.77
    bourg
    0.75
     LET
    0.71
    Activations Density 0.006%

    No Known Activations