© 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. 11535
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to combat and military themes

    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
     challeng
    -0.75
     compe
    -0.64
     referen
    -0.59
    bern
    -0.59
     glim
    -0.59
     corrid
    -0.58
     suspic
    -0.58
     nodd
    -0.58
     millenn
    -0.57
    Jane
    -0.55
    POSITIVE LOGITS
     Parish
    0.89
     Massacre
    0.78
    ®
    0.76
    phia
    0.74
    âĦ¢
    0.73
     Revis
    0.69
     Tribe
    0.69
     Syndrome
    0.67
    ensis
    0.66
     Heights
    0.66
    Activations Density 0.336%

    No Known Activations