© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9319
    Prev
    Next
    INDEX
    Explanations

    numerical patterns indicated by special characters and strings of numbers

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to measurement or statistics

    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
    •GPT2 L10 resid: 'LRRRRRLLRRRL'[:-3]

    No Comments

    Negative Logits
    phant
    -0.73
    ĵĺ
    -0.70
    ĸļ
    -0.69
    phrine
    -0.62
     QC
    -0.62
    cess
    -0.58
    tons
    -0.58
     Logged
    -0.57
     solicit
    -0.57
     WWF
    -0.56
    POSITIVE LOGITS
    idates
    0.84
    aucuses
    0.80
    luster
    0.76
    acia
    0.72
    INA
    0.67
    ular
    0.66
    Ïģ
    0.66
    ULAR
    0.65
    achusetts
    0.64
    usting
    0.64
    Activations Density 0.168%

    No Known Activations