INDEX

Explanations

locations or directions, specifically focusing on directions like "eastern" and "western."

oai_token-act-pair · gpt-3.5-turbo

references to geographic directions, specifically "eastern" and "western"

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

oku

-0.90

vous

-0.89

Sharp

-0.87

tle

-0.85

INAL

-0.85

Poll

-0.83

Applic

-0.83

BALL

-0.81

 istg

-0.80

Deal

-0.78

POSITIVE LOGITS

 hemisphere

1.08

side

0.89

most

0.85

 regions

0.85

 bloc

0.84

 civilization

0.81

 shores

0.81

 Aleppo

0.79

 provinces

0.78

 region

0.77

Activations Density 0.015%

locations or directions, specifically focusing on directions like "eastern" and "western."

references to geographic directions, specifically "eastern" and "western"

No Comments

No Known Activations