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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 20451
    Prev
    Next
    INDEX
    Explanations

    the specific term "photovoltaic" or its abbreviation "PV."

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.66
     McKay
    -0.63
     contrad
    -0.59
     Chall
    -0.59
     cane
    -0.57
     womb
    -0.56
     Maid
    -0.56
     strugg
    -0.56
     barr
    -0.55
     Pelosi
    -0.55
    POSITIVE LOGITS
    ideo
    1.28
    ski
    1.17
    irus
    1.17
    oice
    1.16
    olt
    1.09
    ille
    1.08
    ideos
    1.07
    ascular
    1.02
    igor
    1.01
    iew
    1.01
    Activations Density 0.028%

    No Known Activations