INDEX

Explanations

phrases related to establishing or initiating something

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "set up."

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

obi

-0.77

Brow

-0.71

axe

-0.64

onso

-0.64

doi

-0.64

cold

-0.62

âĨĳ

-0.62

BL

-0.61

hound

-0.61

catentry

-0.60

POSITIVE LOGITS

 tents

0.82

olicy

0.75

 partitions

0.72

 rapport

0.71

dule

0.71

 foundations

0.70

 camp

0.70

 shop

0.69

 banners

0.69

roups

0.67

Activations Density 0.029%

phrases related to establishing or initiating something

instances of the phrase "set up."

No Comments

No Known Activations