© 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. 7-RES-JB
    11. 23532
    Prev
    Next
    INDEX
    Explanations

    words related to authority or expertise

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" and its occurrences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evidence
    -0.77
     Jagu
    -0.72
    Catal
    -0.72
     Vaughan
    -0.69
    guards
    -0.67
     advis
    -0.63
     credits
    -0.62
     Anim
    -0.61
     Insurance
    -0.61
    orange
    -0.61
    POSITIVE LOGITS
     nutshell
    1.03
    rouse
    0.99
     lot
    0.95
     bunch
    0.91
     plethora
    0.90
    versive
    0.90
     multitude
    0.89
    cknowled
    0.88
     certain
    0.87
     nascent
    0.86
    Activations Density 0.403%

    No Known Activations