© 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. 2-RES-JB
    11. 17591
    Prev
    Next
    INDEX
    Explanations

    words related to features, titles, or captions denoting significance or attribution

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating featured or original content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    romy
    -0.85
    rolog
    -0.78
    livion
    -0.77
    tered
    -0.73
    rums
    -0.73
    adows
    -0.72
    osc
    -0.72
     vain
    -0.72
    rene
    -0.71
    pron
    -0.71
    POSITIVE LOGITS
     Dates
    1.18
     Coverage
    1.17
     Definition
    1.14
     Rankings
    1.12
     Rating
    1.11
     Categories
    1.08
     Score
    1.07
     Updates
    1.06
     Points
    1.05
     Characters
    1.05
    Activations Density 0.120%

    No Known Activations