INDEX

Explanations

references to civil conflict or war

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

avorite

-0.78

Tree

-0.75

ournal

-0.74

 Transcript

-0.70

raviolet

-0.65

 Dominion

-0.63

 Whale

-0.62

 Sigma

-0.62

HK

-0.61

 Wicked

-0.60

POSITIVE LOGITS

izational

1.40

isations

1.16

ised

1.03

iza

1.00

ization

1.00

isation

1.00

iz

0.97

 unrest

0.91

izing

0.91

izations

0.90

Activations Density 0.010%

references to civil conflict or war

No Comments

No Known Activations