INDEX

Explanations

information related to military operations and conflicts in various regions

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

Consumer

-0.94

 Lifetime

-0.92

 Consumer

-0.81

 Autism

-0.78

 Oprah

-0.76

 chirop

-0.75

 Consumers

-0.74

Aud

-0.72

ãĤ´ãĥ³

-0.70

 Disclosure

-0.69

POSITIVE LOGITS

 besie

1.28

 siege

1.24

 retake

1.20

 artillery

1.14

 skirm

1.14

 checkpoints

1.14

 Strongh

1.13

 armoured

1.13

 blockade

1.13

 retreating

1.12

Activations Density 0.403%

information related to military operations and conflicts in various regions

No Comments

No Known Activations