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. 3-RES-JB
    6. 21394
    Prev
    Next
    INDEX
    Explanations

    the word "Adidas" and related phrases

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the brand "Adidas" in various 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
    ancial
    -0.87
    ORPG
    -0.75
    ottage
    -0.73
     motions
    -0.71
    ĺħ
    -0.65
     fertility
    -0.65
    ruciating
    -0.64
     supervisors
    -0.64
     trials
    -0.64
     Kaufman
    -0.63
    POSITIVE LOGITS
    idas
    1.19
    é¾įåĸļ士
    0.90
    la
    0.86
     Adidas
    0.86
     jeans
    0.85
    wagon
    0.85
    forth
    0.85
    nee
    0.81
    lash
    0.79
    ão
    0.78
    Activations Density 0.017%

    No Known Activations