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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 4311
    Prev
    Next
    INDEX
    Explanations

    words related to liquid substances, specifically water

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "water" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •a quick list
    words related to liquid substances, specifically water

    No Comments

    Negative Logits
    eering
    -0.87
    Reloaded
    -0.85
    ures
    -0.74
    ablishment
    -0.72
    Files
    -0.70
    ificant
    -0.70
    uary
    -0.68
     Amend
    -0.68
    uler
    -0.65
    -+-+-+-+
    -0.65
    POSITIVE LOGITS
    melon
    1.77
    tight
    1.24
    colour
    1.17
    falls
    1.14
    proof
    1.02
    loo
    0.97
    mel
    0.96
    bowl
    0.95
    color
    0.94
    fall
    0.93
    Activations Density 0.033%

    No Known Activations