© 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. 8-RES-JB
    11. 14872
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the advantages and disadvantages of different situations

    oai_token-act-pair · gpt-3.5-turbo

    discussions of advantages and disadvantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.67
    igraph
    -0.65
    omas
    -0.64
     Registry
    -0.60
    cision
    -0.59
    ogens
    -0.59
    ccording
    -0.58
     Journals
    -0.58
    urgical
    -0.56
    udence
    -0.56
    POSITIVE LOGITS
    Ô
    0.76
     downside
    0.73
     hind
    0.72
     aft
    0.67
     subtract
    0.67
     backward
    0.67
    disable
    0.63
    ether
    0.62
     negatives
    0.62
    eele
    0.61
    Activations Density 0.650%

    No Known Activations