INDEX

Explanations

numerical data and citations within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 maxn

-0.62

inerja

-0.61

 下午

-0.59

 Rptr

-0.57

 Reſ

-0.57

EoL

-0.57

 المعيارى

-0.57

complexContent

-0.56

TemporalType

-0.56

RTCF

-0.56

POSITIVE LOGITS

 INTERESAR

0.57

↑

0.57

//

0.54

millimeters

0.53

__(/*!

0.51

<bos>

0.49

 Ukraina

0.48

 noastre

0.45

檚

0.45

 constitutive

0.45

Activations Density 0.140%

numerical data and citations within a text

No Comments

No Known Activations