© 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. 6-RES-JB
    11. 3019
    Prev
    Next
    INDEX
    Explanations

    mentions or references to individuals with 'ex' in front of their title or position

    oai_token-act-pair · gpt-3.5-turbo

    references to former or past individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zup
    -0.77
     shading
    -0.73
    uden
    -0.73
    kson
    -0.73
    eday
    -0.72
    otle
    -0.71
     intervals
    -0.69
     dances
    -0.68
    utical
    -0.65
    atche
    -0.63
    POSITIVE LOGITS
    girlfriend
    1.13
    husband
    1.04
    imposed
    0.99
    member
    0.96
    president
    0.93
    turned
    0.92
    employ
    0.92
    commun
    0.91
    vict
    0.90
    may
    0.90
    Activations Density 0.024%

    No Known Activations