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. 1-RES-JB
    6. 18877
    Prev
    Next
    INDEX
    Explanations

    words related to the process of evaporation and dissipation

    oai_token-act-pair · gpt-3.5-turbo

    words related to evaporation and degradation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erous
    -0.75
     Venture
    -0.72
     Notting
    -0.68
    legged
    -0.66
    kar
    -0.66
    feature
    -0.65
    BOOK
    -0.65
    holder
    -0.63
     Adventure
    -0.63
    GB
    -0.62
    POSITIVE LOGITS
     evapor
    1.18
     dissip
    0.98
     "$:/
    0.89
    uating
    0.88
    ated
    0.86
    utical
    0.86
    apor
    0.85
    iencies
    0.85
    itri
    0.84
    itates
    0.83
    Activations Density 0.009%

    No Known Activations