INDEX

Explanations

information related to political leaders and their actions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ability

-0.78

 inclusion

-0.72

 oath

-0.70

 util

-0.70

 cens

-0.69

 enqu

-0.68

 capability

-0.67

 waterfall

-0.66

 vocals

-0.66

 censored

-0.64

POSITIVE LOGITS

Advertisement

1.84

Yet

1.56

Newsletter

1.51

But

1.51

Still

1.50

Meanwhile

1.50

Indeed

1.46

Such

1.45

Perhaps

1.45

Nevertheless

1.44

Activations Density 0.493%

information related to political leaders and their actions

No Comments

No Known Activations