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. 6505
    Prev
    Next
    INDEX
    Explanations

    specific county names

    oai_token-act-pair · gpt-3.5-turbo

    references to county designations in a legal or news context

    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
    furt
    -0.88
    Ö¼
    -0.82
    aeus
    -0.82
    isks
    -0.80
    ãĥĦ
    -0.79
    toc
    -0.78
    bub
    -0.77
    ylan
    -0.76
    ipedia
    -0.76
    otten
    -0.75
    POSITIVE LOGITS
     Sheriff
    1.21
     sheriff
    1.10
     District
    1.05
     County
    1.05
     Jail
    1.03
     commissioners
    1.00
     Commissioners
    1.00
    wide
    0.99
     Correctional
    0.97
     Supervisor
    0.97
    Activations Density 0.031%

    No Known Activations