INDEX

Explanations

phrases related to reasons or motivations

oai_token-act-pair · gpt-3.5-turbo

references to motivation and reasons for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

roth

-0.71

gravity

-0.67

ertain

-0.62

GA

-0.61

eer

-0.59

 Present

-0.57

 TRANS

-0.57

dden

-0.56

=-=-=-=-=-=-=-=-

-0.56

UGE

-0.56

POSITIVE LOGITS

 upstream

0.70

retty

0.69

 sometime

0.68

 facult

0.66

 awhile

0.65

 midday

0.65

obe

0.65

©¶æ

0.65

 spor

0.64

ename

0.64

Activations Density 0.600%

phrases related to reasons or motivations

references to motivation and reasons for actions

No Comments

No Known Activations