Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8045
    Prev
    Next
    INDEX
    Explanations

    terms related to reservoirs

    oai_token-act-pair · gpt-3.5-turbo

    mention of water reservoirs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glory
    -0.71
    reme
    -0.71
    Else
    -0.70
    OTO
    -0.68
    azeera
    -0.68
    Ł
    -0.66
    AAAAAAAA
    -0.64
     Pupp
    -0.63
    ihad
    -0.63
    ################################
    -0.63
    POSITIVE LOGITS
     reservoirs
    1.32
     reservoir
    1.29
     basin
    0.95
     Reserv
    0.84
     dams
    0.84
    lain
    0.81
     lakes
    0.74
     wells
    0.72
    myra
    0.71
     Rapids
    0.70
    Activations Density 0.014%

    No Known Activations