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. 0-RES-JB
    6. 23443
    Prev
    Next
    INDEX
    Explanations

    the word "Paolo" with various spellings

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of a specific term or its variations indicative of a particular topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peak
    -0.66
     seat
    -0.61
     hash
    -0.61
     cataly
    -0.61
     loud
    -0.59
     passing
    -0.59
     capacity
    -0.59
     dark
    -0.58
     bright
    -0.58
     line
    -0.58
    POSITIVE LOGITS
    olo
    4.72
    ola
    1.46
    olas
    1.46
    oli
    1.43
    ulo
    1.37
    olini
    1.34
    elo
    1.22
    ol
    1.17
    oro
    1.17
    igi
    1.15
    Activations Density 0.015%

    No Known Activations