© 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. 3009
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of examining or inspecting something closely, often followed by an object of scrutiny

    oai_token-act-pair · gpt-3.5-turbo

    words related to the action of reviewing or evaluating

    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
    apo
    -0.77
    inos
    -0.76
    guard
    -0.76
    ña
    -0.73
    guards
    -0.67
    enos
    -0.67
    Torrent
    -0.67
    wrong
    -0.65
    breakers
    -0.65
    ascal
    -0.65
    POSITIVE LOGITS
     trends
    0.92
     how
    0.92
     whether
    0.88
     footage
    0.84
    ively
    0.80
     histories
    0.80
     clips
    0.79
     existing
    0.78
     carefully
    0.78
     data
    0.78
    Activations Density 0.171%

    No Known Activations