INDEX

Explanations

directional terms indicating locations, specifically focusing on east and west

oai_token-act-pair · gpt-3.5-turbo

references to geographical directions, specifically 'east' and 'west'

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

argon

-0.77

utable

-0.73

Owner

-0.73

 reluct

-0.73

abulary

-0.72

 istg

-0.71

 confir

-0.71

ASED

-0.71

TABLE

-0.70

inventoryQuantity

-0.70

POSITIVE LOGITS

ward

1.35

wards

1.15

side

1.14

 coast

1.00

 hemisphere

0.96

urst

0.86

 west

0.86

west

0.85

bound

0.84

 wing

0.79

Activations Density 0.014%

directional terms indicating locations, specifically focusing on east and west

references to geographical directions, specifically 'east' and 'west'

No Comments

No Known Activations