INDEX

Explanations

references to structured systems and interactions within various contexts

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

Section or figure markers

np_acts-logits-general · gemini-2.0-flash

section numbers and identifiers

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

 Roskov

-0.98

SequentialGroup

-0.96

 CreateTagHelper

-0.95

下载附件

-0.90

хьтан

-0.86

 للمعارف

-0.86

Personensuche

-0.84

ⓧ

-0.83

 nahilalakip

-0.81

ChildScrollView

-0.80

POSITIVE LOGITS

II

1.52

III

1.45

1.23

1.18

VII

1.11

№

1.07

 number

1.06

III

1.04

IV

1.03

 VIII

1.01

Activations Density 1.752%

references to structured systems and interactions within various contexts

Section or figure markers

section numbers and identifiers

No Comments

No Known Activations