INDEX

Explanations

credit references in a text

oai_token-act-pair · gpt-3.5-turbo

the presence of credit or attribution references in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 commute

-0.72

ructose

-0.71

 paved

-0.70

iqueness

-0.69

 attracted

-0.69

odox

-0.69

orrow

-0.68

unci

-0.68

onna

-0.67

oler

-0.67

POSITIVE LOGITS

HAEL

0.77

 Shutterstock

0.75

 Bett

0.72

 Brett

0.71

 COURT

0.69

 Â©

0.69

 Various

0.68

KR

0.68

Phys

0.68

CBC

0.67

Activations Density 0.040%

credit references in a text

the presence of credit or attribution references in the text

No Comments

No Known Activations