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. 3-RES-JB
    6. 1268
    Prev
    Next
    INDEX
    Explanations

    mentions of elephants and related topics such as ivory and elephant seals

    oai_token-act-pair · gpt-3.5-turbo

    references to elephants and related concepts, particularly in conservation contexts

    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
    lly
    -0.89
    nces
    -0.88
    ndra
    -0.86
    nder
    -0.85
    pring
    -0.83
    nergy
    -0.79
    nda
    -0.77
    nd
    -0.74
    lying
    -0.72
    nerg
    -0.72
    POSITIVE LOGITS
     elephant
    1.36
     elephants
    1.31
    iasis
    1.21
     Elephant
    1.09
     herds
    0.90
     poaching
    0.90
     Haram
    0.87
    ota
    0.86
    monary
    0.86
     penis
    0.85
    Activations Density 0.014%

    No Known Activations