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. 20329
    Prev
    Next
    INDEX
    Explanations

    phrases related to government departments, especially in the context of health, human services, housing, and urban development

    oai_token-act-pair · gpt-3.5-turbo

    references to various government departments and their functions

    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
    "]=>
    -0.76
    rely
    -0.67
    jad
    -0.66
    etimes
    -0.65
    fman
    -0.64
    GF
    -0.63
    ilogy
    -0.62
    KER
    -0.62
    aretz
    -0.62
    aeus
    -0.61
    POSITIVE LOGITS
     Instruction
    0.84
    ij士
    0.84
     Corrections
    0.80
     Affairs
    0.79
     Consolid
    0.78
    ertation
    0.76
     Merrill
    0.74
    escription
    0.72
    afort
    0.71
     Service
    0.70
    Activations Density 0.110%

    No Known Activations