© 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. 10-RES-JB
    11. 22165
    Prev
    Next
    INDEX
    Explanations

    text related to policy changes and improvements

    oai_token-act-pair · gpt-3.5-turbo

    statements about political or social challenges and solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weird
    -0.70
    soType
    -0.69
     pecul
    -0.66
     Nom
    -0.66
    ozyg
    -0.65
    gate
    -0.65
     Reported
    -0.64
     discrep
    -0.64
     suscept
    -0.63
     derog
    -0.62
    POSITIVE LOGITS
     requires
    1.17
     achievable
    1.08
     entails
    1.03
     involves
    1.02
     require
    1.00
     elusive
    0.98
    requires
    0.95
     prerequisite
    0.94
     involve
    0.92
     uphill
    0.91
    Activations Density 0.599%

    No Known Activations