INDEX

Explanations

phrases that indicate superlatives or extremes, such as "the oldest," "the highest," or "the largest."

oai_token-act-pair · gpt-3.5-turbo

the presence of "the" with high frequency, indicating a focus on definitive articles and their significance in different contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 aloud

-0.74

earch

-0.69

uate

-0.66

test

-0.64

lins

-0.64

 whence

-0.60

arthed

-0.60

lations

-0.59

Activ

-0.59

uberty

-0.58

POSITIVE LOGITS

 widest

1.04

 capability

1.03

 distinction

1.03

 advantage

1.02

 lowest

1.02

 highest

1.00

 same

1.00

 utmost

1.00

 ability

0.97

 largest

0.96

Activations Density 0.108%

phrases that indicate superlatives or extremes, such as "the oldest," "the highest," or "the largest."

the presence of "the" with high frequency, indicating a focus on definitive articles and their significance in different contexts

No Known Activations