INDEX

Explanations

assertive statements or judgments

oai_token-act-pair · gpt-3.5-turbo

phrases that express safety and certainty

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tons

-0.71

ĸļ

-0.64

listed

-0.63

 Saving

-0.63

 mattered

-0.62

 millenn

-0.58

ories

-0.57

 objectionable

-0.57

 IMAGES

-0.57

pieces

-0.57

POSITIVE LOGITS

 assume

1.39

 conclude

1.24

 speculate

1.15

say

1.07

 presume

1.05

 expect

0.99

 suggest

0.99

 criticize

0.98

 argue

0.98

ask

0.94

Activations Density 0.071%

assertive statements or judgments

phrases that express safety and certainty

No Comments

No Known Activations