INDEX

Explanations

specific terms related to medical conditions and bodily functions

oai_token-act-pair · gpt-3.5-turbo

references to intake-related concepts and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

HCR

-0.72

 Barn

-0.68

stand

-0.65

NRS

-0.64

pton

-0.62

Secondly

-0.61

POS

-0.60

 Coat

-0.60

Bre

-0.59

bery

-0.59

POSITIVE LOGITS

 Intake

1.34

 intake

1.20

 intakes

1.14

 manifold

1.04

ãĥ¼ãĥĨãĤ£

0.99

 manif

0.83

ered

0.78

ħĭ

0.73

eteria

0.73

terness

0.70

Activations Density 0.008%

specific terms related to medical conditions and bodily functions

references to intake-related concepts and measurements

No Comments

No Known Activations