INDEX

Explanations

locations and geographical features, specifically canyons and national parks

oai_token-act-pair · gpt-3.5-turbo

mentions of specific canyons and geographical locations

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

encer

-0.92

encers

-0.86

iencies

-0.85

enced

-0.79

ortun

-0.77

aeus

-0.73

ively

-0.71

lihood

-0.71

iveness

-0.69

ÑĮ

-0.67

POSITIVE LOGITS

 Springs

1.01

 canyon

0.98

 Canyon

0.96

lands

0.91

 Rapids

0.90

Rim

0.86

rim

0.85

 Mesa

0.82

lace

0.80

anyon

0.78

Activations Density 0.031%

locations and geographical features, specifically canyons and national parks

mentions of specific canyons and geographical locations

No Comments

No Known Activations