© 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. 1-RES-JB
    11. 14196
    Prev
    Next
    INDEX
    Explanations

    words related to benefiting or gaining advantage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to benefits and beneficiaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buck
    -0.67
    hunt
    -0.65
     Hole
    -0.65
     Logan
    -0.64
    netflix
    -0.64
    ls
    -0.61
    kar
    -0.61
    gap
    -0.61
     Leather
    -0.60
    UAL
    -0.59
    POSITIVE LOGITS
     benef
    1.32
    iciary
    1.11
    ornia
    0.98
     Benef
    0.93
    icient
    0.92
    benef
    0.91
    itted
    0.90
    doms
    0.84
    eatures
    0.84
     mathemat
    0.84
    Activations Density 0.014%

    No Known Activations