INDEX

Explanations

phrases related to political events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.88

astern

-0.71

è¦ļéĨĴ

-0.66

Beg

-0.66

RFC

-0.65

elf

-0.65

 Shack

-0.64

olicy

-0.63

fortune

-0.63

 Tycoon

-0.62

POSITIVE LOGITS

ysis

1.41

pha

1.12

idad

1.10

ized

1.03

tarian

1.01

tarians

1.01

ised

0.98

icious

0.96

ization

0.95

ities

0.95

Activations Density 0.036%

phrases related to political events

No Comments

No Known Activations