INDEX

Explanations

locations or landmarks near bodies of water

oai_token-act-pair · gpt-3.5-turbo

references to specific lakes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nir

-0.75

ulously

-0.75

ICAL

-0.73

ulate

-0.72

IBLE

-0.71

————

-0.70

CLASSIFIED

-0.70

elist

-0.69

AAAAAAAA

-0.69

edia

-0.64

POSITIVE LOGITS

front

1.17

 Erie

1.11

 Superior

1.05

 Mead

0.95

wood

0.91

 Shore

0.89

 Michigan

0.88

 Zurich

0.87

Tah

0.83

land

0.83

Activations Density 0.020%

locations or landmarks near bodies of water

references to specific lakes

No Known Activations