INDEX

Explanations

phrases involving actions or scenarios that can be performed without a specific requirement or condition

oai_token-act-pair · gpt-3.5-turbo

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

aire

-0.70

oret

-0.61

estern

-0.61

thouse

-0.61

geist

-0.61

Ã¨re

-0.60

 Vald

-0.59

undrum

-0.58

 Kinnikuman

-0.58

sis

-0.58

POSITIVE LOGITS

 necessarily

0.87

 slightest

0.73

 explicitly

0.72

 oneself

0.72

 whatsoever

0.71

 consciously

0.67

obin

0.67

 anymore

0.63

azz

0.63

 anything

0.63

Activations Density 0.134%

phrases involving actions or scenarios that can be performed without a specific requirement or condition

No Comments

No Known Activations