© 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. 12531
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and organizations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to truth and verification in communication

    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
     bothering
    -0.76
    dding
    -0.69
     buzzing
    -0.66
     waning
    -0.65
     lingering
    -0.65
     dwindling
    -0.65
    elight
    -0.65
     fading
    -0.64
     itching
    -0.61
     unanswered
    -0.60
    POSITIVE LOGITS
     consists
    1.19
     utilizes
    1.14
     relies
    1.03
     comprises
    1.02
     represents
    1.01
     differs
    0.99
     incorporates
    0.98
     allows
    0.98
     emphasizes
    0.97
     involves
    0.97
    Activations Density 0.397%

    No Known Activations