INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating missed opportunities or important observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ternity

-0.60

rontal

-0.59

mercial

-0.58

zar

-0.57

 pend

-0.57

artisan

-0.56

imsy

-0.55

mop

-0.54

Tot

-0.54

yes

-0.54

POSITIVE LOGITS

?:

0.93

!?

0.71

]:

0.70

 entails

0.68

 nutshell

0.68

0.67

%:

0.66

Story

0.66

\":

0.66

 boils

0.66

Activations Density 0.340%

names of individuals

phrases indicating missed opportunities or important observations

No Comments

No Known Activations