© 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. 10-RES-JB
    11. 12067
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term "Hill" at varying levels of importance or relevance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alonso
    -0.75
    ============
    -0.64
     oppos
    -0.63
     Bucc
    -0.62
    Export
    -0.62
     unres
    -0.61
     electron
    -0.60
     Norn
    -0.59
    ALLY
    -0.59
    lihood
    -0.58
    POSITIVE LOGITS
    iard
    1.56
    tops
    1.34
    top
    1.31
    side
    1.17
    bill
    1.15
    yer
    1.07
    marks
    1.06
    arious
    1.04
    borough
    1.00
    shire
    0.99
    Activations Density 0.030%

    No Known Activations