INDEX

Explanations

specific scenarios or examples

oai_token-act-pair · gpt-3.5-turbo

references to specific examples or instances in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

¥ŀ

-0.79

itionally

-0.76

ente

-0.72

uld

-0.72

kefeller

-0.71

emetery

-0.69

uesday

-0.68

srf

-0.68

urd

-0.68

uilt

-0.66

POSITIVE LOGITS

cases

0.82

DragonMagazine

0.77

 instance

0.75

mma

0.73

pheus

0.71

 resembles

0.69

 Ambro

0.67

forth

0.66

gue

0.65

case

0.65

Activations Density 0.018%

specific scenarios or examples

references to specific examples or instances in a discussion

No Comments

No Known Activations