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. 10353
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal actions and processes

    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
    hon
    -0.70
     sidx
    -0.66
    swick
    -0.63
    nown
    -0.63
    Mom
    -0.62
    zie
    -0.62
    jri
    -0.61
    cffffcc
    -0.60
    kie
    -0.60
    jab
    -0.59
    POSITIVE LOGITS
     him
    1.04
    enance
    0.92
     them
    0.86
     foreigners
    0.78
     anyone
    0.75
     certain
    0.74
     anybody
    0.73
     whoever
    0.70
     themselves
    0.68
     quotas
    0.68
    Activations Density 0.362%

    No Known Activations