INDEX

Explanations

news article captions or photo credits

oai_token-act-pair · gpt-3.5-turbo

references to images or photographs in a document

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

gae

-0.76

enegger

-0.72

efficients

-0.72

erb

-0.71

ptin

-0.68

 onwards

-0.65

oubtedly

-0.65

 surn

-0.65

reditary

-0.65

obiles

-0.64

POSITIVE LOGITS

0.74

TOP

0.73

Spring

0.72

 Anchorage

0.72

NPR

0.70

PHOTOS

0.68

 NIGHT

0.67

 NETWORK

0.66

COLOR

0.64

 Vaughn

0.64

Activations Density 0.114%

news article captions or photo credits

references to images or photographs in a document

No Comments

No Known Activations