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. 3-RES-JB
    6. 9975
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific river name

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the word "giver" or variations of it

    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
    Downloadha
    -0.70
    avorite
    -0.70
     persisted
    -0.65
     dece
    -0.64
     Display
    -0.61
    elsius
    -0.60
     persistent
    -0.60
    andals
    -0.57
    kef
    -0.57
     deviation
    -0.56
    POSITIVE LOGITS
    iver
    1.20
    ãĤ¡
    0.97
    ãĤ©
    0.92
    ivers
    0.90
    gence
    0.88
    IVER
    0.81
    tainment
    0.80
    çīĪ
    0.79
    atives
    0.78
    acion
    0.77
    Activations Density 0.010%

    No Known Activations