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. 1859
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive qualities, morale, or strength

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "spirit" in various contexts

    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
     Printed
    -0.81
     WATCHED
    -0.72
    PsyNetMessage
    -0.69
    tics
    -0.67
    DERR
    -0.66
     pse
    -0.62
     Parenthood
    -0.61
    theless
    -0.61
     Kessler
    -0.57
    rien
    -0.57
    POSITIVE LOGITS
    uality
    1.10
    ual
    0.92
    uous
    0.85
    uum
    0.74
    atics
    0.72
    lio
    0.72
    atorium
    0.72
    lia
    0.71
    matic
    0.70
    ually
    0.70
    Activations Density 0.020%

    No Known Activations