INDEX

Explanations

phrases related to showcasing or demonstrating something

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

ades

-0.76

kson

-0.71

ataka

-0.65

 newsletters

-0.64

inqu

-0.63

agues

-0.63

scribe

-0.63

aceutical

-0.63

SOURCE

-0.62

oldown

-0.62

POSITIVE LOGITS

ered

0.99

manship

0.99

alter

0.91

 displeasure

0.90

 signs

0.88

biz

0.87

 willingness

0.85

case

0.83

 appreciation

0.80

 dominance

0.74

Activations Density 3.753%

phrases related to showcasing or demonstrating something

No Comments

No Known Activations