INDEX

Explanations

words related to the main topic or focus of a piece of text

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 Rite

-0.76

ooks

-0.75

cia

-0.73

yip

-0.72

olyn

-0.71

oline

-0.71

CLASSIFIED

-0.69

lean

-0.67

zag

-0.64

ADRA

-0.63

POSITIVE LOGITS

ivity

0.93

ivities

0.87

izers

0.83

ivist

0.78

name

0.76

ted

0.76

itatively

0.75

isance

0.72

izer

0.71

imity

0.70

Activations Density 2.434%

words related to the main topic or focus of a piece of text

No Comments

No Known Activations