INDEX

Explanations

comparisons or likenings between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

instances of comparisons and likenesses made between different subjects or ideas

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

oÄŁ

-0.74

Assembly

-0.70

INA

-0.69

ktop

-0.67

IDE

-0.66

noon

-0.65

 oats

-0.64

inth

-0.63

ARM

-0.62

dar

-0.62

POSITIVE LOGITS

isons

0.92

xual

0.89

 favorably

0.80

lihood

0.74

 sidx

0.71

 homosexuality

0.70

uple

0.69

 guiActiveUn

0.68

tones

0.67

 twins

0.67

Activations Density 0.024%

comparisons or likenings between different entities or concepts

instances of comparisons and likenesses made between different subjects or ideas

No Comments

No Known Activations