© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental or sustainable actions

    oai_token-act-pair · gpt-3.5-turbo

    references to reservoir management

    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
     Wim
    -0.77
     oun
    -0.74
     newcom
    -0.71
    xual
    -0.70
     Ãľ
    -0.69
    ategory
    -0.63
     Wag
    -0.62
    heartedly
    -0.62
     '(
    -0.62
     plat
    -0.60
    POSITIVE LOGITS
     Tracker
    0.87
    çİĭ
    0.69
    bilt
    0.69
    ocket
    0.68
    Doctors
    0.66
    Bloomberg
    0.66
    ico
    0.63
    Journal
    0.62
    former
    0.61
    Eye
    0.61
    Activations Density 0.000%

    No Known Activations