INDEX

Explanations

phrases that prompt the reader to recall or remember something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "remember."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

CEO

-0.64

venture

-0.61

Frameworks

-0.61

FO

-0.60

 prec

-0.60

ECD

-0.59

itte

-0.59

DE

-0.58

DN

-0.58

employed

-0.57

POSITIVE LOGITS

remember

1.24

 Remember

1.01

 Recall

0.98

theless

0.93

 remembering

0.89

 remembered

0.88

 Remem

0.86

 remember

0.83

Remember

0.83

 Memories

0.78

Activations Density 0.009%

phrases that prompt the reader to recall or remember something

instances of the word "remember."

No Comments

No Known Activations