INDEX

Explanations

tokens associated with mathematical or programming syntax

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

Often precedes special characters/symbols

np_acts-logits-general · gemini-2.0-flash

numbers or initial characters followed by spaces/words

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

BeginContext

-0.73

хьтан

-0.68

AddTagHelper

-0.63

webElementXpaths

-0.59

 approximate

-0.55

 CanadaChoose

-0.54

اريخ

-0.54

 asume

-0.54

 صوتيه

-0.53

PhysRev

-0.52

POSITIVE LOGITS

 compagni

0.65

 Audiodateien

0.63

 outono

0.62

์ต

0.62



0.61

RetentionPolicy

0.59

-------------</

0.57

 kív

0.55

 borboleta

0.55

 uova

0.54

Activations Density 0.347%

tokens associated with mathematical or programming syntax

Often precedes special characters/symbols

numbers or initial characters followed by spaces/words

No Comments

No Known Activations