Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 6310
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to sticking or holding on

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to attachment and dependency

    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
    oker
    -0.68
    ufact
    -0.66
    ibel
    -0.64
    Rated
    -0.64
    BLIC
    -0.61
    cloth
    -0.61
    FORE
    -0.60
    taining
    -0.60
    plan
    -0.60
    ãĥ£
    -0.60
    POSITIVE LOGITS
     cling
    1.24
     clinging
    0.91
     onto
    0.85
    rily
    0.80
     uncond
    0.77
     pigeon
    0.74
     welf
    0.74
     confinement
    0.71
    shell
    0.71
    attach
    0.71
    Activations Density 0.025%

    No Known Activations