© 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. 9538
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate disagreement or contrast between different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to differing opinions or perspectives

    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
    -+
    -0.73
     Guru
    -0.68
    ocracy
    -0.65
     Donation
    -0.64
    Bound
    -0.61
    \/
    -0.59
    )|
    -0.59
    before
    -0.59
     Registration
    -0.58
    Yo
    -0.58
    POSITIVE LOGITS
     succumb
    0.86
     prefer
    0.80
     succumbed
    0.78
     simply
    0.76
     opted
    0.72
     remain
    0.70
    enes
    0.69
     merely
    0.67
     volunteered
    0.67
     are
    0.67
    Activations Density 0.107%

    No Known Activations