INDEX

Explanations

references to 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

onies

-0.71

aneers

-0.70

ablishment

-0.69

oning

-0.68

chell

-0.66

bil

-0.65

 BART

-0.63

mary

-0.62

annis

-0.62

von

-0.61

POSITIVE LOGITS

Wii

0.88

Switch

0.88

intendo

0.82

ango

0.75

 Hots

0.75

itor

0.74

itsu

0.73

nect

0.73

Nintendo

0.73

FIG

0.73

Activations Density 0.017%

references to the brand "Nintendo."

mentions of the company Nintendo

No Comments

No Known Activations