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. 20301
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to the word 'ashi' with different emphasis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly surnames

    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
    rified
    -0.78
    sworth
    -0.67
    ials
    -0.67
    sheet
    -0.64
    course
    -0.63
     Humans
    -0.61
    papers
    -0.60
    eering
    -0.60
    */(
    -0.59
     Adren
    -0.59
    POSITIVE LOGITS
    ashi
    1.26
    ya
    1.05
    ushi
    0.98
    izu
    0.97
    uchi
    0.94
    qi
    0.93
    ichi
    0.92
    pora
    0.91
    ishi
    0.91
    unta
    0.88
    Activations Density 0.004%

    No Known Activations