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. 8-RES-JB
    6. 17554
    Prev
    Next
    INDEX
    Explanations

    the word "any" followed by a degree of intensity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    the word "any" and similar expressions indicating the concept of quantity or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uploading
    -0.62
     CoC
    -0.61
     Paste
    -0.59
    oria
    -0.55
     summar
    -0.52
     revolt
    -0.51
     Cutter
    -0.51
     Ideal
    -0.51
     Esports
    -0.51
     desperation
    -0.50
    POSITIVE LOGITS
    how
    0.95
    til
    0.89
     mornings
    0.80
    gaard
    0.80
    etheless
    0.79
    times
    0.77
    place
    0.77
    ways
    0.76
     nights
    0.72
    ãĥ¼ãĥĨ
    0.71
    Activations Density 0.199%

    No Known Activations