INDEX

Explanations

phrases indicating a negative impact or worsening of a situation

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate worsening situations or problems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

orsi

-0.71

icipated

-0.69

ELD

-0.67

avage

-0.67

nered

-0.66

atti

-0.65

sha

-0.64

 owes

-0.63

faced

-0.63

airo

-0.62

POSITIVE LOGITS

 easier

1.31

 clearer

1.19

 happen

1.14

 simpler

1.13

 harder

1.10

 worse

1.08

 smoother

1.05

 worthwhile

1.01

 faire

0.98

 safer

0.98

Activations Density 0.076%

phrases indicating a negative impact or worsening of a situation

phrases that indicate worsening situations or problems

No Comments

No Known Activations