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. 11386
    Prev
    Next
    INDEX
    Explanations

    terms related to the primary subject or central concept in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of focus or attention

    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
    Äį
    -0.71
     paradise
    -0.69
     +---
    -0.65
     intest
    -0.63
     decom
    -0.63
    azo
    -0.62
     scraps
    -0.62
    oshenko
    -0.62
     decaying
    -0.62
     cav
    -0.61
    POSITIVE LOGITS
    ORTS
    0.79
     Attention
    0.76
    akers
    0.75
    quickShipAvailable
    0.67
    orial
    0.67
    orically
    0.66
     Lauder
    0.66
    ORGE
    0.66
     specificity
    0.65
     Beir
    0.62
    Activations Density 0.335%

    No Known Activations