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. 3177
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Pal" with various numbers following it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Pal", likely referring to a specific location or entity

    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
    ãĥ¼ãĥĨãĤ£
    -0.89
    ICLE
    -0.72
    REE
    -0.71
    LEASE
    -0.70
    INS
    -0.69
    OOL
    -0.69
    UNE
    -0.65
    IBLE
    -0.65
    éĹĺ
    -0.63
    ãģį
    -0.63
    POSITIVE LOGITS
    estine
    1.21
    atial
    1.16
    myra
    1.06
    adin
    1.06
    grave
    0.99
    agus
    0.98
    mers
    0.94
    atable
    0.92
    amic
    0.89
    agraph
    0.89
    Activations Density 0.012%

    No Known Activations