© 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. 2-RES-JB
    11. 5307
    Prev
    Next
    INDEX
    Explanations

    words related to legal professions or roles

    oai_token-act-pair · gpt-3.5-turbo

    words related to roles and titles of people, particularly those in legal, advising, or supervisory positions

    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
    ©
    -0.79
    printf
    -0.63
    sett
    -0.63
    ©¶æ
    -0.62
    ¥ŀ
    -0.62
     coarse
    -0.62
     understanding
    -0.61
     distinguishing
    -0.60
    param
    -0.60
    follow
    -0.59
    POSITIVE LOGITS
    itor
    1.32
    ious
    1.11
    itors
    1.06
    ial
    1.03
    ium
    0.94
    berus
    0.93
    IAL
    0.92
    ority
    0.86
    iously
    0.86
    abase
    0.85
    Activations Density 0.012%

    No Known Activations