© 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. 4-RES-JB
    11. 14808
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions related to a particular herb - bay leaves

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographic or structural location, particularly "bay."

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

    No Comments

    Negative Logits
    unic
    -0.83
    inous
    -0.75
    iferation
    -0.73
    âĹ¼
    -0.73
     Beir
    -0.71
     Consumers
    -0.71
    gling
    -0.70
    infeld
    -0.69
    ongyang
    -0.67
    urally
    -0.65
    POSITIVE LOGITS
    onet
    1.28
    esian
    0.94
    bay
    0.85
     bay
    0.85
     attendants
    0.77
    oused
    0.76
     Bay
    0.67
    ĺħ
    0.66
    ount
    0.65
    olla
    0.65
    Activations Density 0.008%

    No Known Activations