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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9001
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Palm."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographical location, particularly "Palm" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overrun
    -0.71
     coerc
    -0.66
     mutants
    -0.66
    Train
    -0.63
    arus
    -0.62
     enforced
    -0.62
    arius
    -0.62
     neut
    -0.62
     subscribed
    -0.61
     relativity
    -0.61
    POSITIVE LOGITS
     Palm
    4.13
     palm
    1.75
    Pal
    1.53
     palms
    1.35
     PAL
    1.28
     Pebble
    1.26
     Saras
    1.21
     Brow
    1.21
     Elm
    1.20
     Daytona
    1.19
    Activations Density 0.022%

    No Known Activations