© 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. 0-RES-JB
    11. 15803
    Prev
    Next
    INDEX
    Explanations

    words related to compensatory actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compensation or remuneration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elm
    -0.85
     Windsor
    -0.81
     attendance
    -0.73
    brook
    -0.70
     Entry
    -0.66
    ford
    -0.63
    vez
    -0.62
     Hampton
    -0.61
     Leader
    -0.61
     Hemp
    -0.61
    POSITIVE LOGITS
     compensate
    3.61
     compens
    2.70
     compensated
    2.41
     counteract
    1.37
     recomp
    1.21
     compensation
    1.08
     reimb
    1.08
     rewarded
    1.05
     offsets
    1.01
     Compensation
    1.00
    Activations Density 0.032%

    No Known Activations