© 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. 11-RES-JB
    11. 17330
    Prev
    Next
    INDEX
    Explanations

    phrases related to topics, subjects, debates, or discussions in a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to topics of discussion or subjects of curiosity

    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
    ents
    -0.74
    uez
    -0.66
    ãĥīãĥ©
    -0.65
    PG
    -0.63
     Components
    -0.61
    hing
    -0.61
    ITH
    -0.61
    oline
    -0.61
    frog
    -0.61
    loo
    -0.60
    POSITIVE LOGITS
     fascination
    1.26
     ridicule
    1.26
     contention
    1.20
     ire
    1.16
     discussion
    1.15
     scorn
    1.14
     mockery
    1.13
     conversation
    1.12
     debate
    1.09
     scrutiny
    1.09
    Activations Density 0.121%

    No Known Activations