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. 7059
    Prev
    Next
    INDEX
    Explanations

    words related to geographical or spatial locations, particularly featuring the word "shore"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "shore."

    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
    TM
    -0.68
    cha
    -0.66
    advertising
    -0.65
     Machines
    -0.64
    modules
    -0.63
    ibles
    -0.62
     Nuggets
    -0.60
    rator
    -0.59
     Freddy
    -0.59
    roma
    -0.58
    POSITIVE LOGITS
     shore
    3.85
     shores
    2.12
    shore
    1.80
     coastline
    1.79
     Shore
    1.78
     coast
    1.75
     beaches
    1.55
     beach
    1.51
     coasts
    1.49
     ashore
    1.44
    Activations Density 0.008%

    No Known Activations