INDEX

Explanations

names or terms related to a geographical location, specifically "Akron 6"

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific geographic locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jing

-0.91

eways

-0.88

ulla

-0.85

epad

-0.83

sf

-0.82

itors

-0.79

itism

-0.77

ades

-0.73

ittal

-0.73

icides

-0.73

POSITIVE LOGITS

Buc

0.78

áµ

0.76

keye

0.75

olics

0.73

 Ohio

0.72

keyes

0.72

 Akron

0.71

mega

0.70

OH

0.69

 Cavaliers

0.68

Activations Density 0.039%

names or terms related to a geographical location, specifically "Akron 6"

proper nouns related to specific geographic locations

No Comments

No Known Activations