INDEX

Explanations

phrases related to rankings or positions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ews

-0.71

 overtake

-0.68

ories

-0.68

 uptake

-0.67

snap

-0.67

ossom

-0.67

lag

-0.66

issions

-0.66

inventoryQuantity

-0.66

estyles

-0.65

POSITIVE LOGITS

 unaware

0.92

 Giovanni

0.86

 identified

0.84

 deceased

0.83

 named

0.82

 hired

0.82

 inexperienced

0.79

 elderly

0.79

wolves

0.77

 blinded

0.76

Activations Density 0.331%

phrases related to rankings or positions

No Comments

No Known Activations