INDEX

Explanations

the infinitive form of verbs

oai_token-act-pair · gpt-3.5-turbo

instances of the word "decided to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Detected

-0.83

 IMAGES

-0.75

listed

-0.73

thumbnails

-0.67

 reperto

-0.65

 terminals

-0.64

database

-0.64

 Explan

-0.64

points

-0.63

Lear

-0.63

POSITIVE LOGITS

 settle

1.24

 pursue

1.13

 postpone

1.10

 incorporate

1.04

 give

1.03

 revisit

1.02

 ignore

1.00

 explore

0.99

 donate

0.98

 capitalize

0.97

Activations Density 0.077%

the infinitive form of verbs

instances of the word "decided to."

No Comments

No Known Activations