INDEX

Explanations

the word "that" occurring with a high activation value

oai_token-act-pair · gpt-3.5-turbo

the conjunction "that" in various contexts

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

Tax

-0.66

emis

-0.66

YS

-0.66

tones

-0.62

LIN

-0.62

apolis

-0.62

 Prepar

-0.61

York

-0.60

Tex

-0.58

tam

-0.58

POSITIVE LOGITS

 pesky

0.85

cher

0.83

 translates

0.83

 includes

0.81

 mattered

0.81

milo

0.80

 culminated

0.79

 resulted

0.77

 entails

0.75

 sounds

0.74

Activations Density 0.159%

the word "that" occurring with a high activation value

the conjunction "that" in various contexts

No Comments

No Known Activations