© 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. 2-RES-JB
    11. 23674
    Prev
    Next
    INDEX
    Explanations

    names ending in "-sson"

    oai_token-act-pair · gpt-3.5-turbo

    the suffix 'sson', indicating names or surnames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HIP
    -0.64
     Pax
    -0.61
    ãĥ£
    -0.60
    ocrine
    -0.60
     Sussex
    -0.59
     fet
    -0.58
     utmost
    -0.58
    payers
    -0.57
    course
    -0.56
     peer
    -0.56
    POSITIVE LOGITS
    sson
    1.67
    qv
    0.95
    nir
    0.94
    ansson
    0.94
    ð
    0.94
    kowski
    0.94
    lund
    0.92
    å
    0.89
    strom
    0.83
    nown
    0.82
    Activations Density 0.011%

    No Known Activations