© 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. 2-RES-JB
    11. 6136
    Prev
    Next
    INDEX
    Explanations

    references to political or military occupations

    oai_token-act-pair · gpt-3.5-turbo

    references to "occupation," particularly in political and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    disc
    -0.81
    orah
    -0.74
    dos
    -0.69
    enic
    -0.68
    culated
    -0.67
    ectar
    -0.66
    peak
    -0.65
    dra
    -0.65
    ramid
    -0.65
    lua
    -0.63
    POSITIVE LOGITS
     occupation
    1.02
    eering
    0.98
     occupations
    0.81
     occup
    0.80
    ngth
    0.80
    ATTLE
    0.75
    ãĤ¢ãĥ«
    0.75
     warr
    0.74
     occupying
    0.74
    isans
    0.74
    Activations Density 0.005%

    No Known Activations