INDEX

Explanations

phrases related to showing or displaying information

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "show."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

leans

-0.73

tymology

-0.71

iche

-0.68

wegian

-0.66

undai

-0.66

 politic

-0.63

icult

-0.63

icultural

-0.61

 inhabited

-0.60

retch

-0.60

POSITIVE LOGITS

biz

1.13

runners

1.03

runner

0.90

manship

0.85

alter

0.83

ered

0.81

downs

0.80

mable

0.79

case

0.77

girls

0.77

Activations Density 0.052%

phrases related to showing or displaying information

occurrences of the word "show."

No Known Activations