INDEX

Explanations

programming structures and syntax related to functions and operations

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

C/C++ code-related words

np_acts-logits-general · gemini-2.0-flash

code words and explicit content

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

]='\

-0.50

 shopper

-0.47

 Microb

-0.45

cra

-0.44

TableBody

-0.41

dö

-0.41

Pró

-0.40

 object

-0.39

Pin

-0.37

kendo

-0.37

POSITIVE LOGITS

 kasarigan

0.85

enumii

0.70

 Infórmanos

0.69

enumi

0.67

 стоковая

0.66

 légende

0.64

__;

0.63

 חיצוניים

0.63

 Anſ

0.63

 الدولى

0.63

Activations Density 0.187%

programming structures and syntax related to functions and operations

C/C++ code-related words

code words and explicit content

No Comments

No Known Activations