INDEX

Explanations

phrases indicating justification or appropriateness for an action

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize the concept of making the "right" decision or action

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

oire

-0.67

 uncanny

-0.66

rition

-0.64

ench

-0.64

 streak

-0.63

culosis

-0.63

 exhaustion

-0.63

ooth

-0.62

ipop

-0.61

stasy

-0.60

POSITIVE LOGITS

OPLE

0.80

JUST

0.79

 ..............

0.73

soType

0.71

imaru

0.71

 arrang

0.70

ItemImage

0.70

 ACTIONS

0.67

 practise

0.67

SPONSORED

0.66

Activations Density 0.323%

phrases indicating justification or appropriateness for an action

phrases that emphasize the concept of making the "right" decision or action

No Comments

No Known Activations