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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6664
    Prev
    Next
    INDEX
    Explanations

    phrases related to glamor or glamour

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "glam" or its variations, indicating a focus on glamour or glamour-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Morales
    -0.68
    stood
    -0.63
    tnc
    -0.62
    ilage
    -0.60
     Owl
    -0.58
     reconc
    -0.57
     maintenance
    -0.57
    eeper
    -0.55
     obs
    -0.54
     Gael
    -0.54
    POSITIVE LOGITS
    ming
    1.40
    mer
    1.33
    borgh
    1.28
    mers
    1.14
    ydia
    1.10
    pton
    1.08
    med
    1.06
     Dunk
    0.99
    mable
    0.99
     dunk
    0.98
    Activations Density 0.051%

    No Known Activations