INDEX

Explanations

the word "everywhere"

oai_token-act-pair · gpt-3.5-turbo

the word "everywhere."

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

gotten

-0.76

bal

-0.70

missions

-0.66

rig

-0.66

stood

-0.65

mitting

-0.59

uers

-0.59

GRE

-0.59

estamp

-0.58

quel

-0.58

POSITIVE LOGITS

abouts

1.19

 else

1.18

 Everywhere

1.08

 imaginable

0.97

 Else

0.87

Else

0.84

 except

0.84

upon

0.82

else

0.75

 conceivable

0.75

Activations Density 0.010%

the word "everywhere"

the word "everywhere."

No Comments

No Known Activations