INDEX

Explanations

words related to adversaries or opponents

oai_token-act-pair · gpt-3.5-turbo

the term "opponent" used in various contexts related to conflict or competition

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

olia

-0.83

 Loch

-0.71

erd

-0.70

eret

-0.66

oots

-0.66

mberg

-0.66

umph

-0.65

ocratic

-0.65

itizens

-0.62

acca

-0.62

POSITIVE LOGITS

 batters

0.84

foe

0.80

onent

0.80

 opponent

0.79

 opponents

0.70

 combatants

0.69

hesis

0.68

 vanquished

0.67

onents

0.67

oft

0.67

Activations Density 0.032%

words related to adversaries or opponents

the term "opponent" used in various contexts related to conflict or competition

No Comments

No Known Activations