INDEX

Explanations

statements or predictions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating expectations or recommendations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

GGGGGGGG

-0.65

 Puzzle

-0.64

ITED

-0.63

 syndrome

-0.63

 Syndrome

-0.62

ZI

-0.60

Zah

-0.60

 Patty

-0.58

atile

-0.57

OTO

-0.57

POSITIVE LOGITS

 ideally

1.03

be

1.03

ered

0.99

 clarify

0.85

ering

0.84

othal

0.80

 suffice

0.78

icum

0.78

arget

0.77

 arrive

0.77

Activations Density 0.060%

statements or predictions

phrases indicating expectations or recommendations

No Comments

No Known Activations