INDEX

Explanations

mentions of yards or yard-related activities

oai_token-act-pair · gpt-3.5-turbo

references to yards or outdoor spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

NetMessage

-0.91

omal

-0.72

uten

-0.70

isen

-0.69

ipper

-0.68

onymous

-0.67

uberty

-0.67

emia

-0.65

zai

-0.64

uggage

-0.63

POSITIVE LOGITS

yard

1.11

 yard

0.96

yards

0.87

iage

0.85

igans

0.77

birds

0.76

bridge

0.76

stick

0.74

enium

0.74

stones

0.73

Activations Density 0.007%

mentions of yards or yard-related activities

references to yards or outdoor spaces

No Comments

No Known Activations