© 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. 2-RES-JB
    11. 818
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "PV" which stands for photovoltaic

    oai_token-act-pair · gpt-4-turbo

    terms related to photovoltaic (PV) installations and projects

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic (PV) energy installations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    butt
    -0.87
     scissors
    -0.84
     lick
    -0.75
    bite
    -0.71
    opic
    -0.71
    becue
    -0.70
    shaw
    -0.69
     corpse
    -0.68
    raper
    -0.66
    abba
    -0.66
    POSITIVE LOGITS
     PV
    0.90
    CLASSIFIED
    0.89
    soever
    0.80
    д
    0.77
    dL
    0.76
    slaught
    0.74
     Pon
    0.73
    Reloaded
    0.71
    !/
    0.70
    nis
    0.70
    Activations Density 0.033%

    No Known Activations