INDEX

Explanations

positive expressions related to effort and achievement

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

Follows an imperative verb

np_acts-logits-general · gemini-2.0-flash

actions followed by particles

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

culosis

-0.62

 оригіналу

-0.59

 referenties

-0.57

||

-0.56

CloseOperation

-0.56

 sebelumnya

-0.55

 initComponents

-0.55

tvguidetime

-0.54

IntoConstraints

-0.53

ActionPerformed

-0.53

POSITIVE LOGITS

 pleaſure

0.77

 daily

0.70

 graag

0.68

 fometimes

0.67

 occaf

0.67

LookAnd

0.66

 houſe

0.66

 often

0.65

EnableWeb

0.65

 تانيه

0.62

Activations Density 0.591%

positive expressions related to effort and achievement

Follows an imperative verb

actions followed by particles

No Comments

No Known Activations