Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8009
    Prev
    Next
    INDEX
    Explanations

    references to criminal incidents involving men

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals, particularly mentioning their age

    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
    çļ
    -0.74
     Grid
    -0.69
    ãĤ¦
    -0.68
     Machines
    -0.68
     chars
    -0.67
    ffee
    -0.65
     Journals
    -0.64
     instr
    -0.64
    ellect
    -0.63
    aeda
    -0.62
    POSITIVE LOGITS
    hunt
    1.00
    endez
    0.88
     who
    0.83
    nered
    0.76
     accused
    0.74
     gunman
    0.74
     WHO
    0.74
     SWAT
    0.72
    ishly
    0.71
    ish
    0.70
    Activations Density 0.128%

    No Known Activations