© 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. 2858
    Prev
    Next
    INDEX
    Explanations

    mentions of costumes or cosplay

    oai_token-act-pair · gpt-3.5-turbo

    the word 'cos' and its variations in different contexts

    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
     Hearts
    -0.67
     Lans
    -0.65
     Bulls
    -0.64
     forged
    -0.61
     Giles
    -0.61
     Dah
    -0.61
     Alph
    -0.61
     Beaver
    -0.61
     rake
    -0.61
     Zucker
    -0.60
    POSITIVE LOGITS
    mopolitan
    1.65
    metics
    1.40
    mop
    1.32
    mic
    1.31
    mology
    1.31
    metic
    1.28
    met
    1.19
    mosp
    1.19
    mos
    1.12
    mo
    1.10
    Activations Density 0.027%

    No Known Activations