© 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. 0-RES-JB
    11. 13733
    Prev
    Next
    INDEX
    Explanations

    references to dolls or doll-related items

    oai_token-act-pair · gpt-3.5-turbo

    references to dolls, particularly identifying various types and contexts in which they are mentioned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Solar
    -0.77
     Suc
    -0.74
     Pis
    -0.73
     NAD
    -0.73
    NF
    -0.72
     Carbon
    -0.72
    actic
    -0.71
     Priority
    -0.70
    iris
    -0.68
     ACS
    -0.66
    POSITIVE LOGITS
     doll
    4.00
     dolls
    3.46
     Doll
    2.87
     Barbie
    1.97
     toy
    1.35
     toys
    1.28
     puppet
    1.26
     dummy
    1.25
     figur
    1.25
     pillow
    1.21
    Activations Density 0.032%

    No Known Activations