INDEX

Explanations

phrases related to conflict, struggle, and combat

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

uras

-0.80

essage

-0.79

 Seym

-0.76

ocument

-0.72

ographical

-0.71

ascript

-0.69

Ħ¢

-0.67

amas

-0.66

ardy

-0.64

article

-0.64

POSITIVE LOGITS

 against

1.20

 waged

0.97

 valiant

0.95

 fought

0.94

 raged

0.94

 fiercely

0.92

 tooth

0.91

 battles

0.89

fighting

0.87

fight

0.84

Activations Density 0.681%

phrases related to conflict, struggle, and combat

No Comments

No Known Activations