INDEX

Explanations

instances where a closer examination or inspection is mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to inspecting or analyzing subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

'/

-0.69

 retaliate

-0.69

 interchange

-0.65

 extortion

-0.65

react

-0.61

 Reincarn

-0.60

 Decay

-0.60

CHAPTER

-0.59

AFTA

-0.57

iasis

-0.56

POSITIVE LOGITS

 reveals

1.50

 indicates

1.39

 showed

1.32

 revealed

1.31

 suggests

1.27

 shows

1.22

 confirms

1.21

 indicated

1.19

 yielded

1.18

 uncovered

1.17

Activations Density 0.207%

instances where a closer examination or inspection is mentioned in the text

terms related to inspecting or analyzing subjects

No Comments

No Known Activations