© 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. 6518
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific roles or professions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" within various contexts

    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
     indications
    -0.82
    uses
    -0.80
     Examples
    -0.80
    Effects
    -0.78
    ATURES
    -0.77
     copies
    -0.77
    ItemTracker
    -0.76
     arrangements
    -0.76
    results
    -0.76
     amounts
    -0.75
    POSITIVE LOGITS
     deceased
    0.97
     nutshell
    0.88
     defunct
    0.87
     century
    0.84
     dying
    0.84
     lifetime
    0.83
     nascent
    0.83
     thousand
    0.82
     single
    0.82
     typical
    0.82
    Activations Density 0.210%

    No Known Activations