INDEX

Explanations

phrases related to feelings of intense fear or alarm

oai_token-act-pair · gpt-3.5-turbo

references to feelings of panic or anxiety

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

•layer 1 - fear

No Comments

Negative Logits

ĻĤ

-0.87

Ģ

-0.78

ľ

-0.76

hire

-0.76

detail

-0.74

aver

-0.73

guided

-0.71

href

-0.70

pointers

-0.70

aton

-0.70

POSITIVE LOGITS

 panic

1.20

 Panic

0.98

 hyster

0.92

 pandemonium

0.88

 hysteria

0.84

 earthqu

0.77

 uproar

0.77

ulence

0.75

ulent

0.74

 meltdown

0.72

Activations Density 0.006%

phrases related to feelings of intense fear or alarm

references to feelings of panic or anxiety

No Comments

No Known Activations