© 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. 9882
    Prev
    Next
    INDEX
    Explanations

    abstract or philosophical concepts with an "-ism" suffix

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to art movements, ideologies, and journalism

    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
     DRAG
    -0.74
     DU
    -0.63
     EAR
    -0.63
     Ellen
    -0.61
     Mons
    -0.60
     Mang
    -0.58
    PROV
    -0.58
     Gord
    -0.58
     Cortana
    -0.57
     commencement
    -0.57
    POSITIVE LOGITS
    ism
    3.08
    ist
    3.05
    ists
    2.97
    istic
    2.59
    istically
    2.28
    isms
    2.26
    ISM
    2.08
    IST
    2.01
    istical
    1.92
    istics
    1.80
    Activations Density 0.223%

    No Known Activations