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. 9106
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, specifically focusing on "ahar"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations or names associated with them

    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
     Fusion
    -0.82
    TP
    -0.76
     Fist
    -0.74
    ife
    -0.73
     Robo
    -0.71
     Fedora
    -0.71
     Bike
    -0.70
     Pupp
    -0.67
     Dems
    -0.66
    nc
    -0.66
    POSITIVE LOGITS
    ahar
    2.88
     strat
    2.00
    htar
    1.27
     Mahar
    1.24
     Pratt
    1.19
     Hind
    1.16
     ascend
    1.12
     Mayer
    0.99
     Solomon
    0.98
     Mord
    0.97
    Activations Density 0.068%

    No Known Activations