INDEX

Explanations

instances where something is noticeable or clear, especially in comparison or contrast

oai_token-act-pair · gpt-3.5-turbo

phrases indicating clarity or visibility of a situation or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

umbn

-0.74

aird

-0.71

bey

-0.69

ighth

-0.67

mbuds

-0.66

akin

-0.63

zanne

-0.63

 cons

-0.62

 reins

-0.62

unte

-0.61

POSITIVE LOGITS

iary

1.12

aneously

0.82

||||

0.79

ICLE

0.78

 Signs

0.75

iator

0.75

LY

0.73

eps

0.72

Effects

0.71

Magikarp

0.71

Activations Density 0.066%

instances where something is noticeable or clear, especially in comparison or contrast

phrases indicating clarity or visibility of a situation or condition

No Comments

No Known Activations