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. 2413
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person named Norman in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Norman," particularly in contexts related to filmmaking or controversies surrounding it

    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
    fw
    -0.77
    FW
    -0.72
     Became
    -0.65
     corpus
    -0.63
     timelines
    -0.62
     Decay
    -0.60
    Recomm
    -0.60
     Conserv
    -0.60
    MQ
    -0.59
     Habit
    -0.59
    POSITIVE LOGITS
    loo
    0.82
    ieri
    0.81
    asonic
    0.81
    igne
    0.79
    atos
    0.75
    ragon
    0.75
    ratulations
    0.75
    izational
    0.74
    itbart
    0.74
    pole
    0.73
    Activations Density 0.025%

    No Known Activations