© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11471
    Prev
    Next
    INDEX
    Explanations

    words related to apples or apple-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to apples and related fruit imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GBT
    -0.76
    Param
    -0.75
     Mandal
    -0.72
    vere
    -0.72
     Hague
    -0.68
    vent
    -0.68
    Guard
    -0.63
     Kry
    -0.63
    LR
    -0.63
     WC
    -0.63
    POSITIVE LOGITS
     apples
    3.94
     apple
    3.09
     oranges
    2.17
    apple
    1.91
     grapes
    1.69
     cider
    1.66
     strawberries
    1.44
    Apple
    1.41
     fruits
    1.41
     tomatoes
    1.38
    Activations Density 0.016%

    No Known Activations