INDEX

Explanations

keywords related to caching and cache management

oai_token-act-pair · gpt-3.5-turbo

references to caching mechanisms in computing

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

lihood

-0.80

manship

-0.69

 Asuka

-0.69

nen

-0.66

Aus

-0.65

umar

-0.65

ahu

-0.64

ortun

-0.63

angered

-0.63

apest

-0.63

POSITIVE LOGITS

 cache

1.06

xia

1.02

 Cache

1.00

 caches

0.97

 caching

0.86

Cache

0.86

 storage

0.85

 cached

0.84

cache

0.83

 dumps

0.83

Activations Density 0.016%

keywords related to caching and cache management

references to caching mechanisms in computing

No Comments

No Known Activations