INDEX

Explanations

words related to adversaries or opponents

oai_token-act-pair · gpt-3.5-turbo

mentions of "enemies" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

auntlets

-0.76

eret

-0.75

ced

-0.75

Ħ¢

-0.73

otide

-0.71

oled

-0.65

lic

-0.65

cing

-0.65

med

-0.64

docs

-0.64

POSITIVE LOGITS

foe

1.04

 enemies

1.02

 enemy

0.98

 Enemy

0.94

 Enemies

0.92

 adversaries

0.91

 foes

0.89

hip

0.88

 vanquished

0.86

enemy

0.83

Activations Density 0.013%

words related to adversaries or opponents

mentions of "enemies" in various contexts

No Comments

No Known Activations