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. 10-RES-JB
    6. 11012
    Prev
    Next
    INDEX
    Explanations

    fruits and their related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific fruits, particularly strawberries and tomatoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UAL
    -0.89
    OPER
    -0.79
    trak
    -0.76
    allas
    -0.76
    lasses
    -0.75
    bnb
    -0.70
    iple
    -0.69
    nels
    -0.68
    ional
    -0.68
    mble
    -0.68
    POSITIVE LOGITS
    fruit
    1.21
    berries
    1.10
     juice
    1.10
     tomatoes
    1.07
     bushes
    0.98
    vine
    0.97
     juices
    0.94
     berries
    0.92
     tomato
    0.91
    berry
    0.90
    Activations Density 0.032%

    No Known Activations