INDEX

Explanations

instances where the concept of inactivity or lack of action is mentioned

oai_token-act-pair · gpt-3.5-turbo

references to the concept of inaction or doing nothing

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

aten

-0.81

ipel

-0.66

 Sect

-0.62

roups

-0.62

ardi

-0.61

aturated

-0.60

 Pand

-0.60

 Hacker

-0.59

Fog

-0.58

 passages

-0.58

POSITIVE LOGITS

 wrong

1.07

 proactive

0.99

 else

0.97

 differently

0.93

wrong

0.91

 drastic

0.86

 remotely

0.83

 meaningful

0.82

 unethical

0.82

 stupid

0.81

Activations Density 0.048%

instances where the concept of inactivity or lack of action is mentioned

references to the concept of inaction or doing nothing

No Comments

No Known Activations