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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17259
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophical and sociological concepts, including terms related to causality and materialism

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to causation and fundamental principles in philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ire
    -0.90
    ovember
    -0.90
    quickShipAvailable
    -0.85
    udeb
    -0.79
    Veter
    -0.75
    soDeliveryDate
    -0.75
     showc
    -0.74
     unfocusedRange
    -0.73
    Cmd
    -0.73
    perse
    -0.71
    POSITIVE LOGITS
     beings
    0.96
     atoms
    0.91
     sentient
    0.89
     rationality
    0.88
     philosophers
    0.88
     epist
    0.81
     organisms
    0.80
    rational
    0.80
     atom
    0.79
     Creation
    0.79
    Activations Density 0.728%

    No Known Activations