INDEX

Explanations

texts related to language translation, language proficiency, and language-related programs or initiatives

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

apego

-0.89

ndra

-0.88

urion

-0.84

romeda

-0.82

kefeller

-0.79

roxy

-0.78

vre

-0.77

 Gamble

-0.76

Ara

-0.75

ividual

-0.73

POSITIVE LOGITS

 translation

1.42

 translations

1.32

 diction

1.32

 spoken

1.31

language

1.29

 language

1.27

 subtitles

1.22

 translator

1.19

 interpreter

1.18

 phrases

1.16

Activations Density 1.195%

texts related to language translation, language proficiency, and language-related programs or initiatives

No Comments

No Known Activations