INDEX

Explanations

references to elements of a storyline or narrative

oai_token-act-pair · gpt-3.5-turbo

references to "plot" or narrative structures in texts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agles

-0.67

Downloadha

-0.64

 saline

-0.62

IDA

-0.62

Rio

-0.62

 salts

-0.61

ĪĴ

-0.60

 Splash

-0.58

coh

-0.58

 Jazz

-0.58

POSITIVE LOGITS

ters

1.02

sov

0.85

 Plot

0.82

ting

0.78

ning

0.78

ter

0.77

 twists

0.76

 Twist

0.75

line

0.75

 plotting

0.75

Activations Density 0.023%

references to elements of a storyline or narrative

references to "plot" or narrative structures in texts

No Comments

No Known Activations