INDEX

Explanations

the word "a."

oai_token-act-pair · gpt-3.5-turbo

instances of the article "a."

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

bugs

-0.79

achu

-0.74

Edit

-0.73

agents

-0.73

acid

-0.71

eous

-0.70

books

-0.70

Arcade

-0.68

ATURES

-0.67

 Adin

-0.67

POSITIVE LOGITS

 handful

1.12

lot

1.05

 consequ

1.05

 slew

1.01

cknowled

0.99

 plethora

0.99

 couple

0.98

few

0.98

 huge

0.94

 bunch

0.94

Activations Density 0.184%

the word "a."

instances of the article "a."

No Comments

No Known Activations