© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 13497
    Prev
    Next
    INDEX
    Explanations

    people in positions of authority or leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to "man in the middle" attacks and related vulnerabilities

    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
    DragonMagazine
    -0.79
     Transcript
    -0.74
     externalToEVAOnly
    -0.68
    fml
    -0.65
    TPP
    -0.65
    essional
    -0.65
    essions
    -0.64
     ACTIONS
    -0.63
     approvals
    -0.62
    interstitial
    -0.62
    POSITIVE LOGITS
     whom
    0.81
     himself
    0.70
     ape
    0.68
    who
    0.67
     Aberdeen
    0.67
    hunt
    0.66
    ghai
    0.65
    hat
    0.64
    ku
    0.63
    Jr
    0.63
    Activations Density 0.606%

    No Known Activations