© 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. 2291
    Prev
    Next
    INDEX
    Explanations

    specific details or items within a broader context or category

    oai_token-act-pair · gpt-3.5-turbo

    references to specific details or elements 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
    ublic
    -0.76
    ulton
    -0.76
    ĺħ
    -0.73
     Alive
    -0.72
    frog
    -0.72
     Feldman
    -0.69
    ruary
    -0.68
    former
    -0.68
    adays
    -0.68
    tackle
    -0.67
    POSITIVE LOGITS
    ities
    1.10
     identifiable
    0.97
    ties
    0.91
    ivity
    0.91
     embodiments
    0.89
     wording
    0.89
    iveness
    0.85
    iating
    0.85
     kinds
    0.85
    iations
    0.85
    Activations Density 0.031%

    No Known Activations