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. 9-RES-JB
    6. 6467
    Prev
    Next
    INDEX
    Explanations

    terms related to the surname "Braz" with varying levels of prominence

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the substring 'raz' and variations of the name 'Paul.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sabha
    -0.82
     Antar
    -0.70
    ptic
    -0.68
    lete
    -0.65
    amins
    -0.64
    CLE
    -0.64
    folk
    -0.64
    ½
    -0.62
    XT
    -0.60
    urse
    -0.60
    POSITIVE LOGITS
    xual
    0.94
    iflower
    0.90
    Downloadha
    0.84
    ing
    0.79
    quet
    0.73
    iate
    0.71
     Parables
    0.69
    ingly
    0.69
    inian
    0.69
    evidence
    0.68
    Activations Density 0.102%

    No Known Activations