© 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. 8-RES-JB
    11. 17757
    Prev
    Next
    INDEX
    Explanations

    profession titles in different fields such as engineering, medicine, and academia

    oai_token-act-pair · gpt-3.5-turbo

    occupations or roles relating to various professional fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouls
    -0.80
    uld
    -0.73
    ombies
    -0.73
    éĹĺ
    -0.72
    Players
    -0.69
     needles
    -0.68
    acters
    -0.68
    Ire
    -0.65
    plings
    -0.65
     iPads
    -0.64
    POSITIVE LOGITS
     specializing
    1.20
     extraord
    1.14
     whose
    1.02
    turned
    0.90
     who
    0.86
     adjunct
    0.82
    digy
    0.81
     nicknamed
    0.80
     acquaintance
    0.79
     chemist
    0.78
    Activations Density 0.191%

    No Known Activations