INDEX

Explanations

phrases related to investigation and exploration

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

borough

-0.72

SPONSORED

-0.72

ibr

-0.70

wen

-0.70

nesty

-0.70

 theirs

-0.69

owl

-0.67

tackle

-0.67

boro

-0.66

ranged

-0.66

POSITIVE LOGITS

 workings

1.39

 origins

1.32

 complexities

1.25

 pitfalls

1.22

 nuances

1.21

 basics

1.20

 intric

1.19

 beginnings

1.15

 finer

1.15

 motivations

1.12

Activations Density 0.295%

phrases related to investigation and exploration

occurrences of the word "the"

No Comments

No Known Activations