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. 8455
    Prev
    Next
    INDEX
    Explanations

    words related to bathroom facilities

    oai_token-act-pair · gpt-3.5-turbo

    words related to toilet facilities and sanitation issues

    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
     forth
    -0.81
    CVE
    -0.79
    udic
    -0.70
    */(
    -0.70
    earchers
    -0.68
    )=(
    -0.67
     Flavoring
    -0.66
    ozy
    -0.64
    adena
    -0.63
     accur
    -0.60
    POSITIVE LOGITS
     toilets
    0.88
     bowl
    0.84
     toilet
    0.83
    ysis
    0.80
    bowl
    0.80
     plun
    0.80
     cleaner
    0.79
    rogen
    0.76
     bowls
    0.74
    washer
    0.74
    Activations Density 0.016%

    No Known Activations