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. 14090
    Prev
    Next
    INDEX
    Explanations

    mentions of people providing care or assistance in different scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to roles and responsibilities associated with public service and safety

    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
    ocry
    -0.68
     champagne
    -0.66
    onyms
    -0.66
    æĺ
    -0.64
    eton
    -0.64
    çīĪ
    -0.63
     Wine
    -0.63
    intent
    -0.62
    ceivable
    -0.62
     ABV
    -0.62
    POSITIVE LOGITS
     duties
    1.05
     overseeing
    0.98
     guarding
    0.98
     protecting
    0.92
     assisting
    0.90
     duty
    0.89
     Assist
    0.86
     guiding
    0.83
    keeping
    0.81
     aids
    0.81
    Activations Density 0.671%

    No Known Activations