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. 23087
    Prev
    Next
    INDEX
    Explanations

    phrases related to fantasy or science fiction movie titles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    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
    staking
    -0.82
    sterdam
    -0.68
    furt
    -0.67
     toget
    -0.66
     indulge
    -0.66
    fully
    -0.66
    Downloadha
    -0.65
    rade
    -0.65
    icho
    -0.65
    etheless
    -0.65
    POSITIVE LOGITS
     Law
    0.78
     same
    0.78
     Philippines
    0.78
     Rockies
    0.77
     largest
    0.76
     smallest
    0.76
     Past
    0.75
     Balance
    0.74
     Hill
    0.74
     Netherlands
    0.74
    Activations Density 0.294%

    No Known Activations