© 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. 2733
    Prev
    Next
    INDEX
    Explanations

    legal or political terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or political contexts

    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
    ream
    -0.62
     understandably
    -0.58
    lict
    -0.54
     Princ
    -0.53
     amazed
    -0.53
     Slater
    -0.53
     Bulgar
    -0.52
     thrilled
    -0.52
     doubtless
    -0.52
    wage
    -0.51
    POSITIVE LOGITS
     thereof
    1.41
     altogether
    1.07
     thereto
    0.98
     versa
    0.94
    )?
    0.90
    ?).
    0.86
    itaire
    0.79
     depending
    0.77
    abouts
    0.75
     oneself
    0.74
    Activations Density 0.936%

    No Known Activations