© 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. 2-RES-JB
    11. 9060
    Prev
    Next
    INDEX
    Explanations

    mentions of reservoirs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of reservoirs and related infrastructure

    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
    Else
    -0.82
     Ogre
    -0.77
    ################
    -0.75
    AAAAAAAA
    -0.68
    urn
    -0.68
     Glory
    -0.68
    uro
    -0.68
    MRI
    -0.65
    bart
    -0.63
    cko
    -0.63
    POSITIVE LOGITS
     reservoirs
    1.38
     reservoir
    1.32
     dams
    0.81
     municip
    0.75
     Reserv
    0.74
    tub
    0.73
    ulic
    0.73
     lakes
    0.73
     gauge
    0.72
    electric
    0.72
    Activations Density 0.016%

    No Known Activations