© 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. 3166
    Prev
    Next
    INDEX
    Explanations

    names of public figures and terms related to hacking and security

    oai_token-act-pair · gpt-3.5-turbo

    instances of notable individuals and events related to public controversies

    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
    âķIJâķIJ
    -0.52
     Supported
    -0.49
     Kinnikuman
    -0.49
     pestic
    -0.49
     Attribution
    -0.48
    VIDIA
    -0.48
     opio
    -0.47
     incorpor
    -0.46
    ItemThumbnailImage
    -0.45
    urgical
    -0.44
    POSITIVE LOGITS
     onto
    0.73
    gently
    0.64
    selves
    0.64
     goodbye
    0.63
     into
    0.61
    Downloadha
    0.58
    onto
    0.57
    izont
    0.54
     havoc
    0.54
    pes
    0.53
    Activations Density 1.240%

    No Known Activations