INDEX

Explanations

references to the company GE

oai_token-act-pair · gpt-3.5-turbo

mentions of the company GE (General Electric)

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ±

-0.86

ties

-0.78

ifier

-0.76

ities

-0.74

ãĥ£

-0.74

itarian

-0.73

hips

-0.73

shake

-0.72

ãĤ§

-0.72

iak

-0.71

POSITIVE LOGITS

ORGE

1.35

ICO

0.75

vity

0.74

 Healthcare

0.73

 Stephens

0.71

ECH

0.68

ARY

0.67

 PowerPoint

0.67

utenant

0.67

 Tigers

0.67

Activations Density 0.038%

references to the company GE

mentions of the company GE (General Electric)

No Comments

No Known Activations