INDEX

Explanations

words related to difficulty or intensity

oai_token-act-pair · gpt-3.5-turbo

references to different types or variations of "per."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ichick

-0.66

 foundations

-0.60

ADRA

-0.60

akes

-0.59

 Carbuncle

-0.59

issors

-0.59

orthy

-0.59

 pneum

-0.59

ä¸ī

-0.58

osp

-0.58

POSITIVE LOGITS

cussion

1.01

manent

0.99

due

0.99

taining

0.96

intendent

0.91

ceptions

0.89

vier

0.86

vasive

0.85

ception

0.85

secution

0.83

Activations Density 0.017%

words related to difficulty or intensity

references to different types or variations of "per."

No Comments

No Known Activations