© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    phrases related to enjoyment or having a good time

    oai_token-act-pair · gpt-3.5-turbo

    references to enjoyment or fun in various 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
    ainer
    -0.73
    idate
    -0.70
    ãĥĺãĥ©
    -0.69
    Availability
    -0.68
     defic
    -0.66
    acid
    -0.65
     Lama
    -0.65
    Software
    -0.63
     Centauri
    -0.62
    士
    -0.61
    POSITIVE LOGITS
    nels
    1.67
    nell
    1.39
    gal
    1.27
    nel
    1.09
    ctor
    0.99
    ctors
    0.98
    ctory
    0.94
    icular
    0.93
    pmwiki
    0.92
    eral
    0.89
    Activations Density 0.043%

    No Known Activations