INDEX

Explanations

terms related to caching and cache management

oai_token-act-pair · gpt-3.5-turbo

terms related to caching in computing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

borough

-0.74

 Asuka

-0.70

iates

-0.66

fell

-0.66

 Gundam

-0.65

igans

-0.65

 Narc

-0.64

arios

-0.64

kees

-0.64

boats

-0.62

POSITIVE LOGITS

xia

0.94

zilla

0.82

 misses

0.79

oute

0.79

utical

0.78

 cache

0.78

resses

0.77

utic

0.75

 Cache

0.72

ress

0.71

Activations Density 0.077%

terms related to caching and cache management

terms related to caching in computing

No Comments

No Known Activations