© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4522
    Prev
    Next
    INDEX
    Explanations

    words related to retaining, hiring, or changing jobs

    oai_token-act-pair · gpt-3.5-turbo

    words related to training and retraining processes

    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
    wild
    -0.68
     Hub
    -0.66
     Utility
    -0.63
     Corridor
    -0.62
     Territories
    -0.62
     LW
    -0.62
     Hour
    -0.61
     Christensen
    -0.60
     eminent
    -0.60
     interconnected
    -0.59
    POSITIVE LOGITS
    eval
    0.89
    heet
    0.83
    VERTISEMENT
    0.74
    rarily
    0.73
    lash
    0.69
    naires
    0.69
    escription
    0.69
    dated
    0.67
    DragonMagazine
    0.66
    ardon
    0.66
    Activations Density 0.073%

    No Known Activations