© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10233
    Prev
    Next
    INDEX
    Explanations

    phrases related to fluids and leaking

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions associated with flow or movement in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ldom
    -0.72
    alty
    -0.71
    sey
    -0.64
    alion
    -0.64
    ional
    -0.60
    ahime
    -0.60
    rition
    -0.59
    TD
    -0.58
     handling
    -0.58
    phasis
    -0.57
    POSITIVE LOGITS
     across
    0.99
     onto
    0.97
     everywhere
    0.93
     forth
    0.88
     ashore
    0.88
     around
    0.85
     omin
    0.85
     emanating
    0.84
     beneath
    0.84
     underneath
    0.81
    Activations Density 0.199%

    No Known Activations