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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 15110
    Prev
    Next
    INDEX
    Explanations

    symbols or symbolic representations

    oai_token-act-pair · gpt-3.5-turbo

    words that denote symbols or symbolic representations

    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
     Oaks
    -0.66
    isode
    -0.65
     oats
    -0.63
    cker
    -0.63
    ieri
    -0.62
    ULTS
    -0.62
     Lank
    -0.60
    alsh
    -0.59
    SOURCE
    -0.59
     Grave
    -0.58
    POSITIVE LOGITS
    ically
    1.02
    izes
    0.93
    ized
    0.90
     symbols
    0.88
    icons
    0.83
     Meaning
    0.83
    hips
    0.82
     symbol
    0.82
    istically
    0.81
    izing
    0.81
    Activations Density 0.021%

    No Known Activations