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. 13662
    Prev
    Next
    INDEX
    Explanations

    photovoltaic related terms, specifically focusing on the term "photovoltaic" itself

    oai_token-act-pair · gpt-3.5-turbo

    terms related to photovoltaic technology

    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
    bub
    -0.73
    stasy
    -0.72
    KNOWN
    -0.68
    earch
    -0.66
    bara
    -0.65
    dress
    -0.64
    perse
    -0.63
    fman
    -0.63
    sembly
    -0.62
    eworks
    -0.62
    POSITIVE LOGITS
    olt
    1.01
    age
    0.98
    aire
    0.93
    aic
    0.92
    ting
    0.81
    zman
    0.80
    bolt
    0.76
    ischer
    0.74
    ron
    0.73
    robe
    0.71
    Activations Density 0.016%

    No Known Activations