Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 987
    Prev
    Next
    INDEX
    Explanations

    phrases related to increasing, promoting, or advancing something

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing or enhancing something, particularly in an economic or productivity context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.77
    士
    -0.73
    present
    -0.73
     Mortal
    -0.73
    rors
    -0.72
     WATCHED
    -0.67
    ________________________
    -0.65
    Maps
    -0.65
    andro
    -0.65
     Notting
    -0.63
    POSITIVE LOGITS
     boost
    0.95
     boosting
    0.95
    boost
    0.88
    xual
    0.80
     tremend
    0.79
     boosts
    0.78
    ollen
    0.77
     boosted
    0.77
     Boost
    0.76
     boosters
    0.75
    Activations Density 0.012%

    No Known Activations