INDEX

Explanations

phrases related to wars or military conflicts

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "war" and its related contexts

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

obook

-0.75

Row

-0.74

aminer

-0.73

icles

-0.70

erd

-0.70

Wiz

-0.70

Choice

-0.70

ocl

-0.68

ocracy

-0.68

 kinderg

-0.68

POSITIVE LOGITS

lords

0.85

0.77

 Patton

0.77

0.76

lord

0.76

 Churchill

0.76

era

0.76

0.75

 Norton

0.74

Activations Density 0.053%

phrases related to wars or military conflicts

mentions of the word "war" and its related contexts

No Comments

No Known Activations