© 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. 22704
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence or absence of specific elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to presence or existence in different 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
    rison
    -0.64
    isks
    -0.63
    ategory
    -0.63
    COL
    -0.63
    Cow
    -0.62
    ainers
    -0.62
    ECK
    -0.62
    ourses
    -0.62
    ederal
    -0.61
    '>
    -0.61
    POSITIVE LOGITS
     antit
    0.68
    pport
    0.65
    sole
    0.64
     incidentally
    0.64
    Rated
    0.62
     footing
    0.60
     genetically
    0.60
     compatible
    0.60
    est
    0.58
     habitable
    0.57
    Activations Density 0.452%

    No Known Activations