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. 11277
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or actions involving physical contact

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement and expressions of joy

    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
    mel
    -0.83
    nery
    -0.82
    cms
    -0.79
    si
    -0.79
    xy
    -0.79
    yon
    -0.77
    chin
    -0.77
    xus
    -0.76
    bal
    -0.75
    pps
    -0.74
    POSITIVE LOGITS
     bananas
    0.82
    GGGGGGGG
    0.78
     exha
    0.76
     behavi
    0.73
     Squid
    0.72
     elbows
    0.71
     uphill
    0.71
     ducks
    0.70
     Lizard
    0.69
     turtle
    0.68
    Activations Density 0.179%

    No Known Activations