INDEX

Explanations

phrases related to social interactions

oai_token-act-pair · gpt-3.5-turbo

business-related terminology and expressions

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

uma

-0.70

sole

-0.68

repl

-0.67

aware

-0.65

amar

-0.62

 contracted

-0.62

lav

-0.62

say

-0.59

rans

-0.59

 Accessed

-0.58

POSITIVE LOGITS

 notch

0.73

eh

0.70

 offensively

0.68

ðŁĳ

0.67

;)

0.64

 ðŁĳ

0.63

!.

0.62

 understatement

0.62

!:

0.62

Activations Density 0.339%

phrases related to social interactions

business-related terminology and expressions

No Comments

No Known Activations