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. 22826
    Prev
    Next
    INDEX
    Explanations

    references to specific legal systems or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and names associated with excitement or conflict

    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
    itable
    -0.90
    yip
    -0.78
     cannon
    -0.75
     disclaim
    -0.73
    zik
    -0.73
    ould
    -0.73
    ble
    -0.70
    conservancy
    -0.70
    ball
    -0.69
    table
    -0.68
    POSITIVE LOGITS
    ively
    0.91
    alez
    0.82
    gow
    0.75
    OWER
    0.73
    iveness
    0.71
    iar
    0.67
    ority
    0.67
     warr
    0.66
    daq
    0.66
     endings
    0.66
    Activations Density 0.044%

    No Known Activations