INDEX

Explanations

ampersand '&' symbols that connect items or concepts

oai_token-act-pair · gpt-3.5-turbo

conjunctions or phrases indicating connections or relationships between ideas

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

atche

-0.78

 misunder

-0.69

iguous

-0.66

senal

-0.64

 mattered

-0.63

assian

-0.62

adra

-0.62

 concentrating

-0.62

 tense

-0.61

orable

-0.60

POSITIVE LOGITS

 Friends

0.89

Co

0.89

GAN

0.83

 Associates

0.81

 Sons

0.74

 Partners

0.74

optional

0.73

nect

0.72

 Company

0.72

^^^^

0.69

Activations Density 0.049%

ampersand '&' symbols that connect items or concepts

conjunctions or phrases indicating connections or relationships between ideas

No Known Activations