INDEX

Explanations

phrases related to movement or travel

oai_token-act-pair · gpt-3.5-turbo

phrases involving the concept of "making one's way."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rique

-0.83

Mub

-0.67

 cher

-0.67

erva

-0.67

vol

-0.67

anton

-0.66

 lett

-0.66

insk

-0.66

umb

-0.65

rone

-0.65

POSITIVE LOGITS

DragonMagazine

0.95

Cooldown

0.76

NetMessage

0.75

YD

0.74

 upstream

0.71

istani

0.67

WARD

0.67

Via

0.66

 circulate

0.65

Eva

0.64

Activations Density 0.020%

phrases related to movement or travel

phrases involving the concept of "making one's way."

No Comments

No Known Activations