© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1696
    Prev
    Next
    INDEX
    Explanations

    phrases related to public speeches and formal addresses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of formal speeches or presentations

    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
    axis
    -0.62
     rehabilit
    -0.60
    oil
    -0.58
    IER
    -0.58
     prohib
    -0.58
     untreated
    -0.56
     axis
    -0.55
     cached
    -0.55
     inhibitor
    -0.55
     resilient
    -0.54
    POSITIVE LOGITS
    xual
    0.76
    ebus
    0.75
    esta
    0.75
    ¥µ
    0.73
     Address
    0.73
    urated
    0.72
    eteria
    0.72
    enture
    0.71
    undo
    0.69
    orial
    0.69
    Activations Density 0.017%

    No Known Activations