INDEX

Explanations

phrases starting with "In"

oai_token-act-pair · gpt-3.5-turbo

the phrase "In" followed by a statement or context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.71

 looms

-0.66

 lodged

-0.63

 nailed

-0.61

 spoil

-0.61

reon

-0.61

:/

-0.59

 unlocks

-0.58

 revoked

-0.58

 endors

-0.57

POSITIVE LOGITS

 addition

1.30

flation

1.24

juries

1.22

 spite

1.22

 contrast

1.20

herent

1.19

jured

1.16

sofar

1.13

clusion

1.13

ventory

1.11

Activations Density 0.156%

phrases starting with "In"

the phrase "In" followed by a statement or context

No Comments

No Known Activations