INDEX

Explanations

instances where multiple entities or concepts are described as being the same

oai_token-act-pair · gpt-3.5-turbo

references to the concept of sameness or shared characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ttes

-0.89

skirts

-0.86

 Provided

-0.85

xtap

-0.83

zy

-0.83

flex

-0.83

usa

-0.80

itely

-0.79

rection

-0.76

bane

-0.75

POSITIVE LOGITS

 thing

0.93

 basic

0.85

 nationality

0.82

 amount

0.82

 sentence

0.82

 wavelength

0.81

 molecule

0.81

 geographical

0.81

 organism

0.81

 exact

0.80

Activations Density 0.053%

instances where multiple entities or concepts are described as being the same

references to the concept of sameness or shared characteristics

No Comments

No Known Activations