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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 8160
    Prev
    Next
    INDEX
    Explanations

    phrases related to the city of Munich

    oai_token-act-pair · gpt-3.5-turbo

    the word "hen" in various contexts

    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
    BILITIES
    -0.80
     eleph
    -0.73
     Afric
    -0.62
    ````
    -0.61
     NX
    -0.61
    EED
    -0.60
    cffffcc
    -0.60
     GEAR
    -0.60
    ULTS
    -0.59
    Äĩ
    -0.58
    POSITIVE LOGITS
    cyclopedia
    1.12
    thal
    1.03
    zhen
    0.96
    vironment
    0.95
    ocide
    0.91
    nai
    0.91
    ning
    0.90
    ergy
    0.87
    kov
    0.86
    chen
    0.84
    Activations Density 0.020%

    No Known Activations