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. 0-RES-JB
    6. 21088
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning the idea of 'voices'

    oai_token-act-pair · gpt-3.5-turbo

    references to diverse perspectives or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ée
    -0.75
    NRS
    -0.70
     Schedule
    -0.70
    pletion
    -0.68
    estate
    -0.68
     Cache
    -0.65
    cheat
    -0.64
     Upgrade
    -0.62
    imgur
    -0.62
    urchase
    -0.60
    POSITIVE LOGITS
     voices
    4.07
     voice
    2.36
     Voices
    2.24
    voice
    1.80
     Voice
    1.58
     voiced
    1.55
     whispers
    1.54
    Voice
    1.52
     vocals
    1.47
     voicing
    1.45
    Activations Density 0.008%

    No Known Activations