INDEX

Explanations

mentions of individuals in military uniforms

oai_token-act-pair · gpt-3.5-turbo

instances of "in a" followed by descriptions involving uniforms or clothing

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ESA

-0.69

ebin

-0.67

once

-0.67

onics

-0.65

ICO

-0.65

 Creatures

-0.64

onto

-0.62

Pwr

-0.62

RAM

-0.62

MAP

-0.62

POSITIVE LOGITS

 jeans

1.35

 camouflage

1.30

 robes

1.29

 sunglasses

1.29

 fatig

1.29

 uniform

1.24

 disguise

1.21

 trousers

1.17

 suits

1.12

 shorts

1.10

Activations Density 0.098%

mentions of individuals in military uniforms

instances of "in a" followed by descriptions involving uniforms or clothing

No Known Activations