INDEX

Explanations

phrases that provide formal identifiers or descriptions of entities, particularly names and their classifications or attributes

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

 متعلقه

-0.80

 Monfieur

-0.79

 <=",

-0.78

 فريبيس

-0.76

 ComVisible

-0.70

 صوتيه

-0.69

цездатний

-0.67

 Meksiku

-0.66

पया

-0.66

 onPage

-0.66

POSITIVE LOGITS

ⓘ

0.52

CloseOperation

0.48

0.47

Ops

0.45

ˈ

0.43

 simply

0.43

<b>

0.41

also

0.41

0.40

 heureuse

0.40

Activations Density 0.156%

phrases that provide formal identifiers or descriptions of entities, particularly names and their classifications or attributes

No Comments

No Known Activations