INDEX

Explanations

references to specific names or titles

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

ending in "or" or "OR"

np_acts-logits-general · gemini-2.0-flash

words ending in 'or' or 'tor'

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.88

Gambas

-0.80

ItemBackground

-0.78

 Réponses

-0.76

RenderAtEndOf

-0.74

ResumeLayout

-0.73

 مرئيه

-0.73

 تضيفلها

-0.72

 мәкалә

-0.72

 препратки

-0.71

POSITIVE LOGITS

0.64

ror

0.59

CPtr

0.51

por

0.48

ior

0.48

POR

0.48

or

0.48

rhe

0.47

rer

0.47

PRNewswire

0.46

Activations Density 0.183%

references to specific names or titles

ending in "or" or "OR"

words ending in 'or' or 'tor'

No Comments

No Known Activations