INDEX

Explanations

references to the concept of something being "in" a certain state or condition

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 alike

-0.71

 distingu

-0.63

 inclined

-0.62

 suscept

-0.58

 overcame

-0.57

 convol

-0.57

 obedient

-0.56

 absorbs

-0.55

cia

-0.55

 behaves

-0.55

POSITIVE LOGITS

escap

1.35

humane

1.13

versely

1.01

 jeopardy

1.01

 fact

1.00

authent

0.98

ked

0.97

built

0.94

bred

0.93

lined

0.93

Activations Density 0.141%

references to the concept of something being "in" a certain state or condition

the preposition "in" across various contexts

No Comments

No Known Activations