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. 4826
    Prev
    Next
    INDEX
    Explanations

    references to the brand "La Sportiva"

    oai_token-act-pair · gpt-3.5-turbo

    the term "iva" and its variations, indicating a focus on a specific brand or context related to that term

    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
    unders
    -0.85
     earnest
    -0.70
     clipboard
    -0.69
     prevailing
    -0.66
     incumbent
    -0.64
    */(
    -0.63
     negotiators
    -0.63
    umbnail
    -0.63
    awed
    -0.63
    frames
    -0.62
    POSITIVE LOGITS
    iva
    1.34
    ivas
    1.08
    ption
    0.94
    ishi
    0.90
    ione
    0.89
    isa
    0.89
     tion
    0.89
    ahu
    0.87
    Äį
    0.87
    arov
    0.86
    Activations Density 0.005%

    No Known Activations