INDEX

Explanations

phrases related to governmental positions, administrative bodies, and political issues

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

inventoryQuantity

-0.85

dad

-0.65

)}

-0.65

ĪĴ

-0.65

this

-0.64

Guard

-0.64

 anymore

-0.63

laughs

-0.63

 regrets

-0.62

else

-0.62

POSITIVE LOGITS

 varied

0.70

 eclectic

0.70

 diverse

0.63

 sleek

0.62

 distinctive

0.59

krit

0.59

 consist

0.59

 meticulously

0.59

undown

0.58

 orally

0.58

Activations Density 0.820%

phrases related to governmental positions, administrative bodies, and political issues

No Comments

No Known Activations

phrases related to governmental positions, administrative bodies, and political issues

No Comments

No Known Activations