INDEX

Explanations

mentions of specific locations or addresses

oai_token-act-pair · gpt-3.5-turbo

recurrent use of the word "the."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.67

 comprom

-0.65

 fortun

-0.65

avorite

-0.64

 helicop

-0.63

 destro

-0.62

HCR

-0.61

 Vaugh

-0.61

 advoc

-0.61

edly

-0.60

POSITIVE LOGITS

 Context

0.77

 largeDownload

0.72

 Zombies

0.68

 context

0.67

 nutshell

0.66

 galaxy

0.66

 midst

0.64

 Robots

0.62

Psy

0.61

 Markets

0.61

Activations Density 0.101%

mentions of specific locations or addresses

recurrent use of the word "the."

No Comments

No Known Activations