INDEX

Explanations

modal verbs indicating possibility or permission

oai_token-act-pair · gpt-3.5-turbo

the word "might" and its various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

cies

-0.75

 Leah

-0.74

ament

-0.68

Kik

-0.64

 Palest

-0.62

 Lauder

-0.61

 Kush

-0.60

 Patterson

-0.58

 Reporting

-0.58

amines

-0.58

POSITIVE LOGITS

ily

1.27

 someday

1.09

 wanna

0.96

haps

0.96

iest

0.94

 feas

0.92

 conce

0.90

 plaus

0.89

bes

0.86

 offend

0.86

Activations Density 0.077%

modal verbs indicating possibility or permission

the word "might" and its various contexts

No Comments

No Known Activations