INDEX

Explanations

words related to specific countries involved in conflicts

oai_token-act-pair · gpt-3.5-turbo

references to the Iraq and Syria conflicts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

atin

-0.89

thereum

-0.74

iple

-0.73

bery

-0.71

 newcom

-0.68

onym

-0.68

haw

-0.67

Wim

-0.64

rotein

-0.64

ateur

-0.64

POSITIVE LOGITS

 ravaged

0.79

 Reconstruction

0.73

 Syndrome

0.73

 milit

0.71

 invaded

0.70

 annex

0.69

istan

0.68

 flared

0.66

 looms

0.66

 devastated

0.66

Activations Density 0.122%

words related to specific countries involved in conflicts

references to the Iraq and Syria conflicts

No Known Activations