© 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. 7874
    Prev
    Next
    INDEX
    Explanations

    web domains or websites

    oai_token-act-pair · gpt-3.5-turbo

    references to online networks or platforms

    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
    =-=-=-=-
    -0.72
     payable
    -0.65
     bottled
    -0.64
     Judd
    -0.64
    herty
    -0.63
    ================================================================
    -0.63
     guarant
    -0.63
     snowball
    -0.60
    attled
    -0.59
    âĺħâĺħ
    -0.58
    POSITIVE LOGITS
    anyahu
    1.38
    izens
    1.36
    izen
    1.27
    working
    1.26
    works
    1.22
    sov
    1.14
    WORK
    1.07
    tle
    1.06
    ted
    0.98
    tering
    0.95
    Activations Density 0.021%

    No Known Activations