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. 4-RES-JB
    6. 5024
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "readily."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating availability or accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tags
    -0.84
     Anthem
    -0.75
    ammy
    -0.74
    ICAN
    -0.72
    ongyang
    -0.71
     cornerstone
    -0.70
    lav
    -0.70
    arya
    -0.70
    anwhile
    -0.69
    grave
    -0.68
    POSITIVE LOGITS
    entimes
    0.83
     admits
    0.83
     absorbs
    0.77
     admit
    0.75
     appreciated
    0.75
     admitted
    0.75
     accommod
    0.75
    ensical
    0.74
     testify
    0.74
     accessible
    0.74
    Activations Density 0.009%

    No Known Activations