INDEX

Explanations

comparative adjectives indicating a high degree or quality

oai_token-act-pair · gpt-3.5-turbo

phrases describing types or categories of things

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

 VIDEOS

-0.76

ilaterally

-0.64

 Vulkan

-0.63

å§«

-0.63

 Bars

-0.61

ampions

-0.58

 Colleg

-0.54

heid

-0.54

ior

-0.53

omer

-0.53

POSITIVE LOGITS

liest

1.00

etting

0.88

linger

0.72

lihood

0.70

hest

0.69

lies

0.68

 thing

0.67

est

0.67

hots

0.67

ĸ

0.65

Activations Density 0.039%

comparative adjectives indicating a high degree or quality

phrases describing types or categories of things

No Comments

No Known Activations