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. 7429
    Prev
    Next
    INDEX
    Explanations

    mentions of the company EA in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company EA (Electronic Arts)

    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
    ician
    -0.79
    folk
    -0.75
    icians
    -0.74
    lines
    -0.73
    Magikarp
    -0.69
    erville
    -0.68
    ovych
    -0.67
    gling
    -0.64
    hips
    -0.64
    ahead
    -0.63
    POSITIVE LOGITS
     SPORTS
    1.18
     Sports
    0.89
    SEA
    0.83
    VE
    0.80
    ITH
    0.76
    endi
    0.76
    HR
    0.75
    adden
    0.74
    uates
    0.74
    ZI
    0.72
    Activations Density 0.019%

    No Known Activations