INDEX

Explanations

a variety of terms and phrases related to diversity or multiple options

oai_token-act-pair · gpt-3.5-turbo

terms associated with diversity and variation in topics

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

prints

-0.78

abad

-0.77

mit

-0.69

ylan

-0.68

MIT

-0.68

agate

-0.68

 Walls

-0.67

iquette

-0.66

 Tycoon

-0.64

ndra

-0.62

POSITIVE LOGITS

 ranging

0.86

 sorts

0.79

 degrees

0.78

 varying

0.76

 unspecified

0.75

 different

0.74

 conting

0.72

 kinds

0.70

 variety

0.70

 iterations

0.68

Activations Density 0.060%

a variety of terms and phrases related to diversity or multiple options

terms associated with diversity and variation in topics

No Comments

No Known Activations