INDEX

Explanations

instances of the word "lifetime"

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "lifetime."

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

Tags

-0.84

 Zimmer

-0.75

anooga

-0.74

arity

-0.73

 Hide

-0.71

ī

-0.69

ramid

-0.69

mented

-0.67

NEY

-0.66

uffy

-0.64

POSITIVE LOGITS

 lifetime

1.01

 experien

0.79

 expectancy

0.77

 Achievement

0.76

wcs

0.75

theless

0.73

 lashes

0.73

 destro

0.72

ago

0.72

 Lifetime

0.72

Activations Density 0.006%

instances of the word "lifetime"

references to the concept of "lifetime."

No Comments

No Known Activations