INDEX

Explanations

mentions of a decrease in rank or position

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dem" or related variations, indicating a focus on themes related to democracy or democratic processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WAYS

-0.87

Pull

-0.71

akeru

-0.70

hetti

-0.70

gerald

-0.69

tis

-0.69

URN

-0.67

ORY

-0.67

OWS

-0.67

à¤¾

-0.65

POSITIVE LOGITS

agogue

1.11

agog

1.07

ilit

0.95

dem

0.94

ographically

0.94

ploy

0.92

onym

0.88

igration

0.87

otions

0.87

onse

0.86

Activations Density 0.005%

mentions of a decrease in rank or position

instances of the word "dem" or related variations, indicating a focus on themes related to democracy or democratic processes

No Comments

No Known Activations