INDEX

Explanations

instances of instructions or rules in the context of participation challenges or memes

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

Followed by a number or symbol

np_acts-logits-general · gemini-2.0-flash

nominations, nominees, nominated

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

kript

-0.54

__":

-0.53

 jegy

-0.51

fige

-0.49

μβ

-0.47

ransition

-0.47

mės

-0.47

cripción

-0.46

__':

-0.46

noz

-0.45

POSITIVE LOGITS

 nominations

0.66

 nominees

0.66

 Nomination

0.65

RenderAtEndOf

0.65

 nomination

0.61

 nominated

0.61

 Nominations

0.61

 nominating

0.61

Pautan

0.59

 tagged

0.59

Activations Density 0.195%

instances of instructions or rules in the context of participation challenges or memes

Followed by a number or symbol

nominations, nominees, nominated

No Comments

No Known Activations