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. 1516
    Prev
    Next
    INDEX
    Explanations

    Occurences of the word "Pal" or variations of the word "Pal" like "pals" or in contexts like "Paypal."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pal" in various contexts

    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
    REE
    -0.76
    rss
    -0.72
    rated
    -0.71
    ettings
    -0.69
    lez
    -0.68
    ahead
    -0.67
    hered
    -0.66
     confir
    -0.65
    rees
    -0.64
    definition
    -0.64
    POSITIVE LOGITS
    estine
    1.13
    adin
    1.06
    mere
    0.91
    adium
    0.88
    bara
    0.81
    mer
    0.78
    der
    0.78
    cohol
    0.78
    ilitary
    0.78
    atos
    0.74
    Activations Density 0.013%

    No Known Activations