© 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. 11-RES-JB
    11. 18795
    Prev
    Next
    INDEX
    Explanations

    phrases related to sustainability and business models

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sustainability and challenges facing publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lump
    -0.61
     nick
    -0.60
    sembly
    -0.58
    itive
    -0.55
    commun
    -0.54
     surpr
    -0.52
     coincidence
    -0.51
    ukong
    -0.50
    nick
    -0.49
    Mess
    -0.48
    POSITIVE LOGITS
    entimes
    0.63
    èĪ
    0.57
    ãĤ¶
    0.56
    hire
    0.56
    DragonMagazine
    0.55
    phis
    0.55
    umbnails
    0.54
    osion
    0.54
    Ĺ
    0.53
    iral
    0.53
    Activations Density 0.019%

    No Known Activations