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. 4-RES-JB
    6. 3866
    Prev
    Next
    INDEX
    Explanations

    locations, specifically places mentioned with city names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the city name "Vancouver" in various contexts

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

    No Comments

    Negative Logits
    worldly
    -0.74
    emonic
    -0.71
    irection
    -0.71
    heet
    -0.69
    lift
    -0.68
    enary
    -0.66
    sth
    -0.64
    igen
    -0.63
    reated
    -0.63
     conversions
    -0.62
    POSITIVE LOGITS
     Calif
    0.78
    SEA
    0.77
     Rout
    0.76
    Jr
    0.70
     Nev
    0.69
     Moroc
    0.68
     Chili
    0.68
     Dock
    0.66
     Sheriff
    0.65
     Mayor
    0.65
    Activations Density 0.306%

    No Known Activations