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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 16710
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific location, particularly "Charleston"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location Charleston and associated names

    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
    cles
    -0.95
    itsch
    -0.81
    omen
    -0.71
    oglu
    -0.69
     Bust
    -0.67
    kson
    -0.67
    ome
    -0.66
    wik
    -0.66
    Syria
    -0.66
    lez
    -0.66
    POSITIVE LOGITS
    sburg
    0.96
    ritch
    0.95
    ottesville
    0.88
    ultz
    0.84
    itudes
    0.82
    ulhu
    0.74
    owship
    0.73
    ains
    0.73
    achusetts
    0.72
     mant
    0.71
    Activations Density 0.039%

    No Known Activations