INDEX

Explanations

words related to physical locations or buildings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IGHTS

-0.79

ABE

-0.70

seys

-0.69

soDeliveryDate

-0.67

ield

-0.64

orders

-0.62

edi

-0.62

ickers

-0.62

itsu

-0.61

Ö¼

-0.61

POSITIVE LOGITS

pieces

1.21

piece

1.04

 fielder

1.00

point

0.79

lets

0.79

bard

0.77

stadt

0.76

burst

0.72

arius

0.72

fold

0.71

Activations Density 1.831%

words related to physical locations or buildings

No Comments

No Known Activations