Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 20222
    Prev
    Next
    INDEX
    Explanations

    occurrences of "At" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    multiple uses of the phrase "At" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alpha
    -0.69
    clean
    -0.67
    aceutical
    -0.64
     benefited
    -0.64
    FTWARE
    -0.63
     nailed
    -0.61
    adoes
    -0.60
    tools
    -0.59
     thereof
    -0.58
    Tube
    -0.58
    POSITIVE LOGITS
     least
    1.17
    mosp
    1.06
    hens
    0.96
    kinson
    0.93
     times
    0.87
    chieve
    0.83
    ention
    0.82
    onement
    0.82
    £ı
    0.82
    roph
    0.79
    Activations Density 0.059%

    No Known Activations