INDEX

Explanations

the word "Nice"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Nice" and its variations, indicating a positive sentiment

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

WIND

-0.85

Ultra

-0.77

aer

-0.75

SUP

-0.71

produced

-0.69

OTT

-0.69

à¨

-0.67

interrupted

-0.67

à©

-0.66

ARY

-0.66

POSITIVE LOGITS

 Nice

1.04

nice

1.01

Nice

0.99

 Guys

0.84

Guy

0.84

 Pictures

0.78

cker

0.73

Ã¯

0.73

hua

0.72

ctions

0.71

Activations Density 0.007%

the word "Nice"

occurrences of the word "Nice" and its variations, indicating a positive sentiment

No Comments

No Known Activations