© 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. 13540
    Prev
    Next
    INDEX
    Explanations

    words related to invasions or aggressive actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to invasions and visits

    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
    ascript
    -0.96
    aterasu
    -0.81
    pel
    -0.81
    ngth
    -0.79
    iness
    -0.79
    talk
    -0.77
    ternity
    -0.76
    cellence
    -0.76
    atron
    -0.73
    onomy
    -0.73
    POSITIVE LOGITS
     alcoholic
    0.83
     spouses
    0.81
     agents
    0.78
     professions
    0.74
     engagements
    0.73
     organisms
    0.72
     mammalian
    0.72
     heights
    0.71
     stars
    0.69
    LY
    0.69
    Activations Density 0.280%

    No Known Activations