INDEX

Explanations

mentions of specific punctuation symbols and keywords in text

oai_token-act-pair · gpt-3.5-turbo

significant numerical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ertodd

-0.77

 Jinping

-0.70

utical

-0.68

ocobo

-0.67

ulkan

-0.65

pie

-0.65

uph

-0.64

nesday

-0.64

ignt

-0.63

uty

-0.61

POSITIVE LOGITS

AUT

0.87

Rare

0.86

Discover

0.84

His

0.83

Louis

0.83

ccording

0.82

Ken

0.82

Writing

0.82

Their

0.81

Hum

0.81

Activations Density 0.890%

mentions of specific punctuation symbols and keywords in text

significant numerical values or measurements

No Comments

No Known Activations