© 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. 7-RES-JB
    11. 23461
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy and governance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating debate or controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estones
    -0.65
     chronological
    -0.60
    Static
    -0.57
     notation
    -0.56
    ixt
    -0.56
    ozo
    -0.56
    leaf
    -0.54
     Ribbon
    -0.54
     folder
    -0.54
    ogly
    -0.54
    POSITIVE LOGITS
    AFP
    0.91
    etheless
    0.76
     ])
    0.68
     REUTERS
    0.68
     rapists
    0.67
    SPONSORED
    0.66
    utterstock
    0.65
    ASHINGTON
    0.65
     Belfast
    0.63
     Tories
    0.63
    Activations Density 0.817%

    No Known Activations