© 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. 3355
    Prev
    Next
    INDEX
    Explanations

    words related to tasks or responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jobs and responsibilities

    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
    osponsors
    -0.82
    avia
    -0.81
    guyen
    -0.75
    vari
    -0.70
    REAM
    -0.69
    upt
    -0.68
    vae
    -0.68
    Flo
    -0.66
    Spread
    -0.65
    Bang
    -0.65
    POSITIVE LOGITS
    manship
    1.14
     entrusted
    1.10
     tasks
    1.02
     delegated
    1.01
     duties
    0.99
     chores
    0.97
    smanship
    0.93
     responsibilities
    0.89
     undertaken
    0.88
     undone
    0.87
    Activations Density 0.096%

    No Known Activations