INDEX

Explanations

locations or directions

oai_token-act-pair · gpt-3.5-turbo

references to geographical regions or directions, particularly the term "north."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

PLIC

-0.80

wcsstore

-0.77

TABLE

-0.77

aminer

-0.75

inventoryQuantity

-0.75

Documents

-0.74

ulous

-0.73

utory

-0.73

inance

-0.71

PRESS

-0.70

POSITIVE LOGITS

ward

1.28

side

1.06

ampton

1.03

western

1.02

west

0.99

wards

0.98

bound

0.95

shore

0.91

urst

0.87

vale

0.86

Activations Density 0.031%

locations or directions

references to geographical regions or directions, particularly the term "north."

No Comments

No Known Activations