INDEX

Explanations

phrases related to requests for assistance or help

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

Code, XML, or configuration snippets

np_acts-logits-general · gemini-2.0-flash

archaic and non-english words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Rüyada

-0.51

autoFocus

-0.48

 поле

-0.47

افع

-0.45

ulele

-0.45

ochlor

-0.45

quera

-0.45

PreInfinity

-0.44

TAKT

-0.43

IBILITIES

-0.42

POSITIVE LOGITS

 kaarangay

0.74

 myſelf

0.71

 perſon

0.69

 beginnetje

0.65

bewerken

0.65

 bezeichneter

0.63

 виправивши

0.63

HomeAsUpEnabled

0.62

 purpoſe

0.62

 fevere

0.62

Activations Density 0.022%

phrases related to requests for assistance or help

Code, XML, or configuration snippets

archaic and non-english words

No Comments

No Known Activations