© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18284
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations within sentences

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the" and its various usages across sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itiz
    -0.73
    ional
    -0.72
    #$
    -0.65
    irds
    -0.64
    abel
    -0.61
    edly
    -0.61
    yet
    -0.61
     owes
    -0.61
    abe
    -0.60
    uty
    -0.58
    POSITIVE LOGITS
     meantime
    1.69
     midst
    1.34
     absence
    1.26
     aftermath
    1.23
     case
    1.05
     ensuing
    1.04
     wake
    1.01
     simplest
    0.96
     meanwhile
    0.96
     context
    0.96
    Activations Density 0.137%

    No Known Activations