INDEX

Explanations

references to the word "Free."

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

The token "Fre" often followed by other characters

np_acts-logits-general · gemini-2.0-flash

words starting with fre

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

ๆ

-0.49

nth

-0.48

ๆ

-0.48

Root

-0.45

non

-0.45

ômico

-0.45

 وسط

-0.44

////////////////

-0.43

 matter

-0.43

POSITIVE LOGITS

PreferredItem

0.78

 للاسماء

0.74

EDEFAULT

0.73

OrBuilder

0.73

Fre

0.73

 Chwiliwch

0.73

 كومونز

0.72

 تضيفلها

0.71

Fre

0.71

RegressionTest

0.70

Activations Density 0.136%

references to the word "Free."

The token "Fre" often followed by other characters

words starting with fre

No Comments

No Known Activations