© 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. 10-RES-JB
    11. 11251
    Prev
    Next
    INDEX
    Explanations

    statements related to legal matters and potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of extreme or significant outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achev
    -0.62
    Firstly
    -0.61
    avery
    -0.61
    CVE
    -0.59
    vironment
    -0.58
    eve
    -0.57
    arta
    -0.57
    aito
    -0.57
    apor
    -0.56
    uncture
    -0.55
    POSITIVE LOGITS
     others
    1.61
     another
    1.54
     other
    1.39
    another
    1.39
     additional
    1.37
     further
    1.37
     subsequent
    1.34
     similarly
    1.23
     Others
    1.22
     Another
    1.19
    Activations Density 1.170%

    No Known Activations