© 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. 6-RES-JB
    11. 1648
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical activities and locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the end of a text segment or paragraph markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perjury
    -0.68
     understatement
    -0.64
     Rosenstein
    -0.63
    raq
    -0.60
     proverb
    -0.59
    -)
    -0.58
     scapego
    -0.58
     ital
    -0.56
     faire
    -0.56
     dictionary
    -0.55
    POSITIVE LOGITS
     mosqu
    0.94
     pilgrims
    0.68
    aneously
    0.67
     earthqu
    0.65
    ertility
    0.63
    ICES
    0.63
    iking
    0.62
     eleph
    0.62
    orthern
    0.61
    kefeller
    0.60
    Activations Density 1.423%

    No Known Activations