INDEX

Explanations

references to geographical locations, specifically canyons and Mesa, Arizona

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical locations, particularly canyons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

SN

-0.70

su

-0.67

TF

-0.67

 analys

-0.66

 deter

-0.65

rik

-0.64

ts

-0.61

 favourable

-0.60

 labou

-0.60

employed

-0.60

POSITIVE LOGITS

 Canyon

4.06

 canyon

2.16

anyon

1.66

 Mesa

1.55

 Creek

1.44

 Cove

1.33

 Yosemite

1.33

 Ranch

1.32

 Cavern

1.24

 Valley

1.23

Activations Density 0.014%

references to geographical locations, specifically canyons and Mesa, Arizona

mentions of specific geographical locations, particularly canyons

No Comments

No Known Activations