INDEX

Explanations

references to the brand "Nintendo."

oai_token-act-pair · gpt-3.5-turbo

mentions of Nintendo

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aneers

-0.70

ablishment

-0.69

onies

-0.67

 Manson

-0.67

oning

-0.66

chell

-0.63

oldemort

-0.62

vae

-0.62

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.61

 McKenna

-0.61

POSITIVE LOGITS

Switch

0.90

Wii

0.87

Nintendo

0.86

intendo

0.86

itive

0.77

itsu

0.77

ango

0.74

nect

0.73

ITE

0.72

Talk

0.72

Activations Density 0.012%

references to the brand "Nintendo."

mentions of Nintendo

No Comments

No Known Activations