INDEX

Explanations

geographical locations, specifically cities or landmarks

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

Äĩ

-0.85

hered

-0.80

sheet

-0.79

glers

-0.78

liness

-0.74

meric

-0.74

ionic

-0.74

acters

-0.73

animate

-0.72

orders

-0.72

POSITIVE LOGITS

 Beach

1.28

 Heights

1.28

 Valley

1.26

 Oaks

1.23

 Hills

1.21

 Park

1.20

 Island

1.16

 Grove

1.12

 Creek

1.11

 Springs

1.08

Activations Density 0.154%

geographical locations, specifically cities or landmarks

No Comments

No Known Activations