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. 22959
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to a person named "Maur" or variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ury" or variations related to it

    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
    eworld
    -0.90
    ocular
    -0.82
    itude
    -0.82
    eared
    -0.80
    artney
    -0.75
    kered
    -0.74
    etermin
    -0.72
    ractive
    -0.70
    omorph
    -0.69
    ional
    -0.68
    POSITIVE LOGITS
    âķIJ
    0.81
    eon
    0.66
    stals
    0.66
     reptiles
    0.65
    outube
    0.65
    stein
    0.65
    bilt
    0.64
    ea
    0.64
     GEAR
    0.64
     Ole
    0.60
    Activations Density 0.014%

    No Known Activations