INDEX

Explanations

terms related to movement and progression

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

"move" or its variations

np_acts-logits-general · gemini-2.0-flash

move or moving to a new place/state

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

Reentrant

-0.53

AndPassword

-0.53

 HasFactory

-0.52

+#+

-0.51

textTheme

-0.51

RTCF

-0.50

GraphicsUnit

-0.50

 sanitarias

-0.49

dao

-0.48

 engraçadas

-0.48

POSITIVE LOGITS

 moves

1.11

 MOVE

1.09

MOV

1.05

 move

1.03

 Move

1.01

 moved

1.00

 Moves

0.98

 forward

0.96

 mover

0.96

 MOVING

0.96

Activations Density 0.096%

terms related to movement and progression

"move" or its variations

move or moving to a new place/state

No Comments

No Known Activations