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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 168
    Prev
    Next
    INDEX
    Explanations

    words related to starvation and famine

    oai_token-act-pair · gpt-4-turbo

    phrases related to hunger and starvation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to starvation and famine

    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
    oral
    -0.83
    allic
    -0.75
    osite
    -0.72
    atre
    -0.70
    rity
    -0.70
    Sphere
    -0.69
    CENT
    -0.69
    aters
    -0.68
    bernatorial
    -0.68
    inion
    -0.68
    POSITIVE LOGITS
     starve
    1.31
     starvation
    1.18
     starving
    1.12
     famine
    1.07
     starved
    1.01
     malnutrition
    0.83
     hunger
    0.83
     ration
    0.82
     miser
    0.79
    wolves
    0.78
    Activations Density 0.017%

    No Known Activations