INDEX

Explanations

words related to politics and government, particularly those related to leadership positions and actions

oai_token-act-pair · gpt-3.5-turbo

repeated occurrences of the letter 'g'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ô

-0.86

tenance

-0.83

terday

-0.78

ĸļ

-0.73

 Dame

-0.71

éĹĺ

-0.68

byter

-0.67

 retrospect

-0.65

 Ruins

-0.64

 Exile

-0.64

POSITIVE LOGITS

ulp

1.22

rosso

1.15

asp

1.11

ourmet

1.08

auntlets

1.05

idd

1.04

ambling

1.03

agging

1.02

aret

1.02

reetings

1.01

Activations Density 0.019%

words related to politics and government, particularly those related to leadership positions and actions

repeated occurrences of the letter 'g'

No Comments

No Known Activations