INDEX

Explanations

specific formatting elements or structures within text, such as lists or enumerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

marshaller

-0.80

mybatisplus

-0.70

Bronnen

-0.70

BagLayout

-0.69

Демографія

-0.68

 AllMovie

-0.57

rschein

-0.56

 թվական

-0.56

Czytaj

-0.55

figsize

-0.55

POSITIVE LOGITS

//

0.81

 }^{*}$

0.79

getOr

0.73

 CanadaChoose

0.70

"}}>

0.67

And

0.65

"):

0.65

 "");

0.64

 Meksiku

0.64

omiast

0.64

Activations Density 0.167%

specific formatting elements or structures within text, such as lists or enumerations

No Comments

No Known Activations