INDEX

Explanations

references to battles and warfare

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

ascript

-0.80

oba

-0.70

essage

-0.63

 livest

-0.62

oci

-0.62

amera

-0.62

ħĭ

-0.61

çīĪ

-0.61

ure

-0.60

gow

-0.60

POSITIVE LOGITS

roy

1.12

cru

1.10

axe

1.03

front

1.03

 waged

1.01

 fought

1.00

 against

0.94

 raged

0.93

 raging

0.88

naire

0.86

Activations Density 0.018%

references to battles and warfare

No Comments

No Known Activations