© 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. 6-RES-JB
    11. 3999
    Prev
    Next
    INDEX
    Explanations

    mentions of internships

    oai_token-act-pair · gpt-3.5-turbo

    instances and mentions of the term "intern."

    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
    gging
    -0.65
     Caucasus
    -0.63
     signalling
    -0.62
    arma
    -0.62
     palms
    -0.62
    foot
    -0.62
     bluff
    -0.61
    irs
    -0.60
     è£ıè¦ļéĨĴ
    -0.59
    akespe
    -0.58
    POSITIVE LOGITS
    ships
    1.52
    ship
    1.04
    ationally
    1.02
     interns
    0.99
    rador
    0.95
    ials
    0.91
    elong
    0.90
    atural
    0.89
     intern
    0.88
    roach
    0.82
    Activations Density 0.020%

    No Known Activations