INDEX

Explanations

specific locations or places mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

locations associated with violent incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

angible

-0.68

source

-0.68

 Vulcan

-0.67

 Grail

-0.64

GMT

-0.63

 stool

-0.62

WIND

-0.60

PLAY

-0.59

BY

-0.58

 Scandinavian

-0.58

POSITIVE LOGITS

 County

1.06

 Bernardino

1.06

icides

0.85

cade

0.84

inia

0.79

ienne

0.77

oche

0.75

olic

0.74

itiz

0.74

 Rica

0.72

Activations Density 0.008%

specific locations or places mentioned in news articles

locations associated with violent incidents

No Comments

No Known Activations