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. 2-RES-JB
    6. 17900
    Prev
    Next
    INDEX
    Explanations

    phrases related to prestigious recognition or awards

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various "Halls of Fame."

    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
    resp
    -0.69
     RN
    -0.65
     Aber
    -0.64
     hem
    -0.63
    nian
    -0.61
    dyl
    -0.60
     Adobe
    -0.60
    acted
    -0.60
     Mass
    -0.59
    hours
    -0.59
    POSITIVE LOGITS
     Fame
    1.33
    rities
    1.03
    ilial
    0.91
     Trophy
    0.87
    isSpecialOrderable
    0.84
    brance
    0.84
    naire
    0.82
     fame
    0.81
     plaque
    0.76
     Bowl
    0.75
    Activations Density 0.009%

    No Known Activations