INDEX

Explanations

elements related to registration, labels, and backend data structures

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

Code snippets and identifiers

np_acts-logits-general · gemini-2.0-flash

data structure keys

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

-0.84

↵↵

-0.83

-0.81

-0.75

-0.72

,"

-0.71

-0.70

),

-0.70

POSITIVE LOGITS

Efq

1.55

 للمعارف

1.40

 CreateTagHelper

1.39

 Theſe

1.33

 myſelf

1.32

 whoſe

1.31

 Jefus

1.31

 disambiguazione

1.30

 Monfieur

1.29

 Anſ

1.29

Activations Density 0.320%

elements related to registration, labels, and backend data structures

Code snippets and identifiers

data structure keys

No Comments

No Known Activations