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. 13574
    Prev
    Next
    INDEX
    Explanations

    phrases related to storytelling and experiences of hardship

    oai_token-act-pair · gpt-3.5-turbo

    common conjunctions and prepositions indicating relationships between phrases or ideas

    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
     Mate
    -0.85
     Knot
    -0.72
     Gong
    -0.67
     Kham
    -0.67
     Wake
    -0.66
     Appeal
    -0.66
     Roe
    -0.64
     Bundy
    -0.63
     Balk
    -0.62
     Buddy
    -0.62
    POSITIVE LOGITS
    selves
    0.96
    terday
    0.94
    redients
    0.92
    mosp
    0.92
    theless
    0.89
    ilogy
    0.88
    etheless
    0.85
    yrinth
    0.80
    istar
    0.79
    umbai
    0.77
    Activations Density 0.226%

    No Known Activations