INDEX

Explanations

instances of the word "see" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

zelfde

-0.63

Cyfeiriadau

-0.57

 interna

-0.57

endregion

-0.56

外部链接

-0.54

ronic

-0.53

siez

-0.53

 تعدى

-0.52

inner

-0.52

RectangleBorder

-0.52

POSITIVE LOGITS

 shew

0.64

 propOrder

0.62

Analyst

0.59

ötzlich

0.58

 opérateur

0.58

 shewn

0.58

NameInMap

0.57

 fhew

0.57

FieldNumber

0.57

cheinend

0.57

Activations Density 0.265%

instances of the word "see" in various contexts

No Comments

No Known Activations