INDEX

Explanations

terms related to computational complexity, particularly regarding intractable and tractable problems in circuit design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ElementException

-0.69

 betweenstory

-0.69

 pleaſure

-0.65

ioutil

-0.60

 BoxFit

-0.60

 voyons

-0.59

 Católica

-0.59

 مشين

-0.58

 configureStore

-0.58

 poffible

-0.58

POSITIVE LOGITS

EDEFAULT

0.55

 resourceCulture

0.54

Portail

0.51

FromArgb

0.48

 发表于

0.47

rute

0.46

vertre

0.45

برا

0.44

loài

0.44

movq

0.43

Activations Density 1.701%

terms related to computational complexity, particularly regarding intractable and tractable problems in circuit design

No Comments

No Known Activations