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. 14392
    Prev
    Next
    INDEX
    Explanations

    words related to technology and features

    oai_token-act-pair · gpt-3.5-turbo

    the prepositions "in" and "of."

    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
     Kills
    -0.62
    ousy
    -0.62
    SPONSORED
    -0.61
    gado
    -0.60
    ONEY
    -0.60
     Phi
    -0.60
    arella
    -0.59
    uca
    -0.59
     Trials
    -0.59
    aido
    -0.58
    POSITIVE LOGITS
    oret
    0.77
    ãĤ´ãĥ³
    0.76
    accessible
    0.72
    alog
    0.71
     newcom
    0.70
    drawn
    0.69
    tenance
    0.67
    vised
    0.65
    strument
    0.64
    -+-+
    0.62
    Activations Density 0.137%

    No Known Activations