INDEX

Explanations

words related to communication and expressing thoughts or opinions

oai_token-act-pair · gpt-3.5-turbo

phrases related to speaking or expressing opinions directly

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

 Landing

-0.67

 Converted

-0.66

gradation

-0.63

uilding

-0.62

 satell

-0.62

ģĸ

-0.62

 Expend

-0.62

 rolls

-0.61

lisher

-0.60

adelphia

-0.60

POSITIVE LOGITS

 louder

0.88

 voic

0.83

 loudly

0.78

 speaker

0.77

 aloud

0.76

english

0.71

 volumes

0.70

 loud

0.69

TED

0.69

 deaf

0.69

Activations Density 0.151%

words related to communication and expressing thoughts or opinions

phrases related to speaking or expressing opinions directly

No Comments

No Known Activations