© 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. 17521
    Prev
    Next
    INDEX
    Explanations

    actions related to taking photographs or selfies

    oai_token-act-pair · gpt-3.5-turbo

    references to taking and sharing photos, particularly selfies

    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
    ensable
    -0.73
    stood
    -0.68
    Beg
    -0.67
    orney
    -0.66
    redict
    -0.65
    onsense
    -0.65
    ifted
    -0.65
    ŃĶ
    -0.61
    answered
    -0.60
    osi
    -0.59
    POSITIVE LOGITS
     selfies
    1.16
     pics
    0.96
     selfie
    0.94
     of
    0.91
     Snapchat
    0.89
     thereof
    0.87
     pictures
    0.87
     photos
    0.84
     snapshots
    0.83
     photograp
    0.83
    Activations Density 0.109%

    No Known Activations