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. 6521
    Prev
    Next
    INDEX
    Explanations

    terms related to technical aspects of a story, such as pacing, plot, balance, controls, and graphics

    oai_token-act-pair · gpt-3.5-turbo

    elements related to storytelling and narrative structure in media

    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
    sonian
    -0.83
    bians
    -0.75
    ascar
    -0.74
    sg
    -0.74
    arnaev
    -0.73
    ulhu
    -0.72
    jon
    -0.72
    20439
    -0.70
    Joined
    -0.69
    Pie
    -0.69
    POSITIVE LOGITS
     irregularities
    1.08
     woes
    0.96
     deficiencies
    0.94
     integrity
    0.93
     conflic
    0.92
     adjustments
    0.92
     adjustment
    0.91
     quirks
    0.89
     issues
    0.89
     calibration
    0.89
    Activations Density 0.822%

    No Known Activations