© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 18203
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "grape" or related concepts such as "vineyards," "growers," and "grapefruit."

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to grapes and grape production

    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
    iaz
    -0.83
    oyer
    -0.83
    ossal
    -0.79
    iazep
    -0.77
    itutional
    -0.75
    ictional
    -0.71
    owicz
    -0.71
    ividually
    -0.71
    urai
    -0.70
     condem
    -0.70
    POSITIVE LOGITS
    fruit
    1.56
    vine
    1.30
     vine
    1.22
     vines
    1.21
     grapes
    1.02
     growers
    1.02
     fruit
    0.99
     tomatoes
    0.98
     plants
    0.91
    leaf
    0.89
    Activations Density 0.020%

    No Known Activations