INDEX

Explanations

phrases expressing agreement with statements

oai_token-act-pair · gpt-3.5-turbo

phrases indicating agreement

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

akin

-0.74

 Dise

-0.71

gins

-0.68

chin

-0.67

liner

-0.66

liners

-0.64

quer

-0.63

mite

-0.63

numbered

-0.62

bodied

-0.61

POSITIVE LOGITS

 regards

0.98

 regard

0.93

¬¼

0.75

asper

0.71

ibel

0.70

 sentiments

0.69

ĪĴ

0.69

ogun

0.68

abus

0.67

hus

0.66

Activations Density 0.056%

phrases expressing agreement with statements

phrases indicating agreement

No Comments

No Known Activations