INDEX

Explanations

terms related to military defense and security

oai_token-act-pair · gpt-3.5-turbo

references to defense-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

piring

-0.65

Bee

-0.63

atta

-0.60

 cups

-0.60

ahon

-0.59

 Lakes

-0.58

liam

-0.57

opping

-0.57

 scenic

-0.57

verning

-0.57

POSITIVE LOGITS

 defense

1.18

defense

1.11

 Defense

1.04

Defense

1.04

 defenses

0.92

 defence

0.92

 DEFENSE

0.89

 contractor

0.84

 attorney

0.81

hement

0.80

Activations Density 0.020%

terms related to military defense and security

references to defense-related topics

No Comments

No Known Activations