INDEX

Explanations

words or phrases followed by a specific symbol

oai_token-act-pair · gpt-3.5-turbo

instances of personal or formal titles and names in the text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.69

cuts

-0.63

 Â®

-0.61

 flaming

-0.59

cat

-0.59

wards

-0.58

================================

-0.57

 Hearts

-0.57

 Canaver

-0.57

 android

-0.56

POSITIVE LOGITS

erion

0.79

eways

0.77

oter

0.74

ogh

0.72

igham

0.71

ouver

0.69

eway

0.69

anchester

0.67

zek

0.65

omatic

0.65

Activations Density 0.248%

words or phrases followed by a specific symbol

instances of personal or formal titles and names in the text

No Comments

No Known Activations