INDEX

Explanations

instances where something is being compared to other things

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the word "other" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.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

-0.65

 Fuji

-0.64

ffee

-0.62

-0.61

-0.60

 ç¥ŀ

-0.58

ister

-0.58

-0.57

 Bride

-0.57

ARS

-0.57

POSITIVE LOGITS

worldly

1.57

swer

0.95

wise

0.94

quickShipAvailable

0.79

etheless

0.77

 kinds

0.76

parts

0.76

types

0.73

 aspects

0.72

 kindred

0.71

Activations Density 0.083%

instances where something is being compared to other things

the repeated mention of the word "other" in various contexts

No Comments

No Known Activations