Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10163
    Prev
    Next
    INDEX
    Explanations

    words related to the surname "sson"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'sson', typically related to names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fet
    -0.66
     Pax
    -0.65
    ocrine
    -0.64
     PLAN
    -0.64
     Sussex
    -0.63
     HIP
    -0.61
     current
    -0.61
    payers
    -0.60
     tense
    -0.58
     NCT
    -0.57
    POSITIVE LOGITS
    sson
    1.60
    ð
    0.96
    ansson
    0.96
    nown
    0.93
    lund
    0.93
    qv
    0.92
    å
    0.90
    nir
    0.86
    kowski
    0.84
    isson
    0.82
    Activations Density 0.012%

    No Known Activations