INDEX

Explanations

repetitive references to a specific term or phrase

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

contentLoaded

-0.85

 للاسماء

-0.66

__':

-0.65

__":

-0.58

PageContext

-0.53

 légales

-0.53

 consultation

-0.52

 protoimpl

-0.52

็จ

-0.51

IsContent

-0.50

POSITIVE LOGITS

ks

1.27

KS

0.85

ksz

0.74

ksh

0.61

KS

0.60

 Services

0.58

EPS

0.57

 bureau

0.57

ksk

0.56

gamon

0.56

Activations Density 0.070%

repetitive references to a specific term or phrase

No Comments

No Known Activations