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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-RES-JB
    6. 1113
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "tide" at varying strengths

    oai_token-act-pair · gpt-3.5-turbo

    references to tides and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disabled
    -0.70
     macros
    -0.63
    imon
    -0.63
     CU
    -0.63
    ":["
    -0.61
     Matth
    -0.60
     [+
    -0.58
    cpp
    -0.58
    Offline
    -0.58
     Mes
    -0.58
    POSITIVE LOGITS
     tide
    4.25
     tides
    3.37
     Tide
    2.51
     tidal
    2.11
     pend
    1.47
     tsunami
    1.32
     wave
    1.25
     currents
    1.20
     flood
    1.13
     waves
    1.12
    Activations Density 0.021%

    No Known Activations