© 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. 11537
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their personal experiences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and struggles

    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
    bris
    -0.66
    hua
    -0.66
    "?
    -0.63
    AIR
    -0.62
    ridge
    -0.62
    avis
    -0.62
    Lock
    -0.61
    clock
    -0.61
    dl
    -0.59
    *)
    -0.59
    POSITIVE LOGITS
     challeng
    1.10
     misconceptions
    1.02
     pitfalls
    0.92
     pros
    0.82
     philosophies
    0.78
     encount
    0.75
     motivations
    0.75
    abouts
    0.73
     obstacles
    0.73
     reluct
    0.71
    Activations Density 0.605%

    No Known Activations