INDEX

Explanations

instances of the word "there"

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "there."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

CJ

-0.75

 Â±

-0.60

 actionGroup

-0.59

 cent

-0.58

 Mecca

-0.58

 Aden

-0.58

ONSORED

-0.57

 cogn

-0.57

 Stras

-0.57

 Bangladesh

-0.56

POSITIVE LOGITS

abouts

1.12

upon

0.90

 guiActiveUn

0.80

ngth

0.79

olkien

0.78

ntil

0.77

fore

0.76

ometimes

0.75

esson

0.74

etheless

0.74

Activations Density 0.140%

instances of the word "there"

the repeated use of the word "there."

No Comments

No Known Activations