© 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. 3621
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements and quantitative assessments

    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
     concludes
    -0.56
    owship
    -0.56
    uez
    -0.55
    rather
    -0.53
    asus
    -0.53
     Liberty
    -0.51
    odied
    -0.50
     fuse
    -0.50
    bis
    -0.49
     concluded
    -0.49
    POSITIVE LOGITS
     anymore
    2.10
     nor
    1.42
     anytime
    1.34
     unless
    1.26
     either
    1.13
    unless
    1.08
    nor
    1.06
     anywhere
    1.02
    yet
    1.01
     any
    0.99
    Activations Density 0.901%

    No Known Activations