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. 17781
    Prev
    Next
    INDEX
    Explanations

    company names with the word "Inc." and potentially financial terms like "damages" and "portfolio"

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
    ultan
    -0.69
     guiActiveUn
    -0.68
     companions
    -0.68
    htaking
    -0.66
     hunter
    -0.66
     cradle
    -0.65
    romy
    -0.63
     cir
    -0.63
     wiser
    -0.60
    icular
    -0.59
    POSITIVE LOGITS
     Ltd
    0.97
     Speedway
    0.84
    ItemTracker
    0.83
     âĵĺ
    0.78
    luaj
    0.70
    XXX
    0.70
    ateral
    0.69
     Released
    0.67
    icio
    0.66
     Akron
    0.66
    Activations Density 0.036%

    No Known Activations