© 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. 6-RES-JB
    11. 15433
    Prev
    Next
    INDEX
    Explanations

    references to various reports and recommendations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "report."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conservancy
    -0.81
    east
    -0.70
    creen
    -0.67
     vow
    -0.63
    cffff
    -0.63
    theless
    -0.62
     gate
    -0.62
     schooling
    -0.61
    ategory
    -0.60
     hypert
    -0.59
    POSITIVE LOGITS
    velop
    0.89
    Crash
    0.83
    report
    0.83
    orial
    0.82
    iry
    0.81
    books
    0.81
    emi
    0.78
    ounces
    0.73
    imony
    0.71
    itle
    0.71
    Activations Density 0.053%

    No Known Activations