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. 12391
    Prev
    Next
    INDEX
    Explanations

    words related to baseball such as 'bat'

    oai_token-act-pair · gpt-3.5-turbo

    references to bats

    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
    ãĥ´ãĤ¡
    -0.97
    xia
    -0.77
    FINE
    -0.75
    zanne
    -0.71
    Ô
    -0.65
    eous
    -0.65
     Publisher
    -0.65
    vre
    -0.65
    oppable
    -0.63
    éĸ
    -0.63
    POSITIVE LOGITS
    tered
    0.90
    bat
    0.80
    manship
    0.78
     bat
    0.77
    chers
    0.76
    ista
    0.75
    oche
    0.75
    bats
    0.74
    hit
    0.73
    cher
    0.72
    Activations Density 0.012%

    No Known Activations