INDEX

Explanations

default values and properties in a structured format

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

Code or data samples containing the word "default"

np_acts-logits-general · gemini-2.0-flash

default values and settings

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

 يتيمه

-0.83

($__

-0.78

OGND

-0.75

 BorderRadius

-0.74

 initComponents

-0.73

 كومونز

-0.71

 convaincre

-0.68

 setShow

-0.68

utilisons

-0.63

مصادر

-0.63

POSITIVE LOGITS

CloseOperation

0.86

情况下

0.74

ing

0.73

值

0.67

 settings

0.63

값

0.61

 setting

0.55

 values

0.54

isation

0.52

値

0.52

Activations Density 0.039%

default values and properties in a structured format

Code or data samples containing the word "default"

default values and settings

No Comments

No Known Activations