© 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. 4-RES-JB
    11. 522
    Prev
    Next
    INDEX
    Explanations

    commands or directives to take action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "issue" in a legal or formal context

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

    No Comments

    Negative Logits
    uph
    -0.78
    lihood
    -0.77
    hattan
    -0.75
    terness
    -0.75
     destro
    -0.67
    atti
    -0.67
     perv
    -0.67
    cosystem
    -0.67
     vibe
    -0.65
    obi
    -0.64
    POSITIVE LOGITS
    ulate
    0.94
    dule
    0.72
    ANGE
    0.70
     Parenthood
    0.69
     monthly
    0.67
     attendance
    0.67
     campuses
    0.66
     additional
    0.66
     amendments
    0.66
     meetings
    0.66
    Activations Density 0.200%

    No Known Activations