INDEX

Explanations

data related to entities that share a common attribute or characteristic

oai_token-act-pair · gpt-3.5-turbo

instances of the word "same" in various contexts

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

zy

-0.72

erest

-0.71

acus

-0.69

 Provided

-0.69

rea

-0.69

Bei

-0.68

ohyd

-0.67

MSN

-0.65

âĵĺ

-0.65

avorite

-0.65

POSITIVE LOGITS

 vein

0.95

 exact

0.86

 thing

0.85

 amount

0.79

 timeframe

0.75

iating

0.72

 spot

0.72

 ballpark

0.72

 kind

0.72

 denomination

0.71

Activations Density 0.040%

data related to entities that share a common attribute or characteristic

instances of the word "same" in various contexts

No Comments

No Known Activations