INDEX

Explanations

phrases indicating action being taken or decisions being made

oai_token-act-pair · gpt-3.5-turbo

instances of the word "made" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assis

-0.68

icals

-0.64

 conditioning

-0.62

sit

-0.60

ively

-0.60

 Adin

-0.60

 stripe

-0.60

 ding

-0.59

 herbs

-0.59

 Route

-0.58

POSITIVE LOGITS

 sure

0.87

solete

0.84

ailable

0.83

unal

0.80

umbles

0.76

emort

0.76

dinand

0.75

roid

0.74

 payable

0.73

gements

0.73

Activations Density 0.069%

phrases indicating action being taken or decisions being made

instances of the word "made" in various contexts

No Comments

No Known Activations