INDEX

Explanations

mentions of the brand "Nintendo."

oai_token-act-pair · gpt-3.5-turbo

mentions of the company Nintendo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ablishment

-0.71

lain

-0.71

aneers

-0.69

chell

-0.69

vae

-0.68

 Manson

-0.67

onies

-0.66

oning

-0.66

annis

-0.64

ynski

-0.63

POSITIVE LOGITS

Switch

0.88

Wii

0.87

intendo

0.83

Nintendo

0.78

 Switch

0.75

itsu

0.75

 Logo

0.74

Hack

0.74

itive

0.72

ango

0.72

Activations Density 0.010%

mentions of the brand "Nintendo."

mentions of the company Nintendo

No Comments

No Known Activations