© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 2592
    Prev
    Next
    INDEX
    Explanations

    references to solar technology, particularly related to solar panels or photovoltaic cells

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic technology and solar panels

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

    No Comments

    Negative Logits
    stasy
    -0.68
    perse
    -0.67
    KNOWN
    -0.66
     misunder
    -0.64
    bara
    -0.63
    sembly
    -0.61
     consideration
    -0.60
     srf
    -0.60
    ccording
    -0.60
     samurai
    -0.59
    POSITIVE LOGITS
    olt
    1.11
    aic
    0.99
    age
    0.91
    aire
    0.86
    ucket
    0.81
    ting
    0.80
    zman
    0.79
    ischer
    0.77
    owered
    0.74
    rolet
    0.73
    Activations Density 0.008%

    No Known Activations