INDEX

Explanations

phrases related to long-standing issues, beliefs, or traditions

oai_token-act-pair · gpt-3.5-turbo

phrases related to longstanding or ongoing issues and practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Stars

-0.81

nesota

-0.77

ooter

-0.76

raph

-0.71

©¶æ

-0.70

asus

-0.68

plet

-0.68

++++

-0.67

achev

-0.67

osponsors

-0.67

POSITIVE LOGITS

 tradition

1.13

 fascination

0.97

 longstanding

0.89

 belief

0.88

 animosity

0.88

 grievances

0.86

 dispute

0.86

 favourite

0.85

 refrain

0.85

stay

0.84

Activations Density 0.081%

phrases related to long-standing issues, beliefs, or traditions

phrases related to longstanding or ongoing issues and practices

No Comments

No Known Activations