© 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. 3-RES-JB
    11. 10761
    Prev
    Next
    INDEX
    Explanations

    financial terms related to activities and merit

    oai_token-act-pair · gpt-3.5-turbo

    indicators of user activity or status within a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brun
    -0.71
     Boe
    -0.65
    ibur
    -0.63
     Fres
    -0.63
    oles
    -0.63
     tant
    -0.61
     Webster
    -0.61
     Holt
    -0.61
     Pag
    -0.60
     Af
    -0.60
    POSITIVE LOGITS
    Merit
    1.65
    ertodd
    1.13
    iculty
    0.94
    ancial
    0.91
    iciary
    0.90
    Offline
    0.85
    onential
    0.84
    Reward
    0.80
    coins
    0.79
    Requirements
    0.79
    Activations Density 0.014%

    No Known Activations