INDEX

Explanations

phrases related to uncertainty or confusion about ongoing events

oai_token-act-pair · gpt-3.5-turbo

phrases expressing uncertainty or inquiry about ongoing situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

heid

-0.67

aments

-0.67

essor

-0.62

ament

-0.61

adjusted

-0.58

urdy

-0.57

cember

-0.57

lication

-0.56

uania

-0.55

mology

-0.55

POSITIVE LOGITS

 wrong

0.77

-|

0.75

 viral

0.75

verning

0.72

 happening

0.71

ggle

0.71

bang

0.70

 forward

0.69

!/

0.68

forth

0.67

Activations Density 0.053%

phrases related to uncertainty or confusion about ongoing events

phrases expressing uncertainty or inquiry about ongoing situations

No Comments

No Known Activations