INDEX

Explanations

phrases related to time durations and actions across time

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anooga

-0.79

ventus

-0.78

ãĥ¤

-0.73

edia

-0.71

omever

-0.68

owler

-0.67

ellar

-0.67

orah

-0.64

articles

-0.63

zsche

-0.62

POSITIVE LOGITS

 captivity

1.08

 uninterrupted

0.94

 probation

0.85

 gestation

0.81

 accumulated

0.80

 campaigning

0.78

 reckoning

0.74

inement

0.73

 touring

0.72

 conditioned

0.72

Activations Density 1.425%

phrases related to time durations and actions across time

No Comments

No Known Activations