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. 1813
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "vis" with varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "vis" and its variations, indicating a focus on visibility or visual representation

    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
    ropy
    -0.67
    rd
    -0.66
    ries
    -0.66
    RAW
    -0.65
    riage
    -0.63
     CLR
    -0.62
    rost
    -0.62
    ¶ħ
    -0.62
     piping
    -0.62
    anyahu
    -0.62
    POSITIVE LOGITS
    ibility
    1.23
    ibly
    1.06
    itors
    0.96
    idon
    0.90
    ited
    0.89
    ibl
    0.86
    itism
    0.86
    udo
    0.86
     versa
    0.86
    IBLE
    0.84
    Activations Density 0.018%

    No Known Activations