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. 8557
    Prev
    Next
    INDEX
    Explanations

    the word "of" followed by various other words

    oai_token-act-pair · gpt-3.5-turbo

    phrases centered around the concept of "ideas."

    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
    WF
    -0.74
     ILCS
    -0.72
    keys
    -0.70
    DAQ
    -0.65
    iaries
    -0.65
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    ï¸ı
    -0.63
    Emb
    -0.63
    CTV
    -0.63
    ECA
    -0.62
    POSITIVE LOGITS
     communism
    0.70
    matically
    0.70
     limitless
    0.69
     donating
    0.68
     marrying
    0.67
     creating
    0.67
    unin
    0.67
    pired
    0.66
     hindsight
    0.66
     quitting
    0.66
    Activations Density 0.114%

    No Known Activations