© 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. 19795
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial costs and burdens

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" and its repeated emphasis, suggesting a focus on specific subjects or concepts

    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
     owned
    -0.71
    andise
    -0.69
    Cod
    -0.68
    owned
    -0.66
    strate
    -0.65
    jong
    -0.65
    rete
    -0.64
    Anim
    -0.64
    Britain
    -0.64
    #$#$
    -0.61
    POSITIVE LOGITS
     temptation
    1.42
     brunt
    1.38
     possibility
    1.38
     inevitable
    1.17
     hassle
    1.16
     slightest
    1.16
     onslaught
    1.16
     inconvenience
    1.15
     pitfalls
    1.15
     dangers
    1.14
    Activations Density 0.304%

    No Known Activations