INDEX

Explanations

patterns in code related to functions and their parameters

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

Capital letters only

np_acts-logits-general · gemini-2.0-flash

programming language syntax

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

 itſelf

-1.30

 Theſe

-1.29

CloseOperation

-1.26

ChildScrollView

-1.24

 myſelf

-1.18

IntoConstraints

-1.17

 חיצוניים

-1.16

 Monfieur

-1.15

 '\\;'

-1.09

 Houſe

-1.06

POSITIVE LOGITS

0.67

0.66

0.63

0.60

0.59

ad

0.59

Activations Density 0.021%

patterns in code related to functions and their parameters

Capital letters only

programming language syntax

No Comments

No Known Activations