© 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. 8-RES-JB
    11. 6072
    Prev
    Next
    INDEX
    Explanations

    phrases related to advanced technology and capabilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential capabilities or functionalities of various objects or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rant
    -0.74
     Lauder
    -0.73
     Irving
    -0.67
     Reasons
    -0.66
    pants
    -0.66
     Federation
    -0.64
     Tradition
    -0.64
     hating
    -0.63
    chel
    -0.62
     Barth
    -0.61
    POSITIVE LOGITS
     withstand
    1.28
    't
    1.28
    adian
    1.15
     handle
    1.14
    berra
    1.11
     penetrate
    1.07
     afford
    1.06
     operate
    1.03
     cope
    1.00
     tolerate
    1.00
    Activations Density 0.168%

    No Known Activations