INDEX

Explanations

dates in the format of year with a high activation value

oai_token-act-pair · gpt-3.5-turbo

specific years mentioned 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

warts

-0.96

wart

-0.81

phia

-0.77

bars

-0.75

ï¸

-0.72

nery

-0.70

yll

-0.69

ongh

-0.69

arist

-0.69

idon

-0.68

POSITIVE LOGITS

å¹

1.22

 partName

0.81

 Remastered

0.78

 Definition

0.76

 Became

0.76

ãĥ¬

0.74

 Admission

0.73

 RELEASE

0.71

00000000

0.70

 Converted

0.70

Activations Density 0.037%

dates in the format of year with a high activation value

specific years mentioned in the text

No Comments

No Known Activations