INDEX

Explanations

phrases related to memory recall and uncertainty

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

first-person hedging and memory-based statements that express uncertainty or tentative belief.

oai_token-act-pair · gpt-5 Triggered by @arielgoldsteinlab

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

awtextra

-0.53

parsedMessage

-0.46

 ExecuteAsync

-0.41

 destru

-0.38

AsUp

-0.36

ViewInit

-0.36

 assurent

-0.35

 MenuView

-0.35

xnn

-0.34

 destructor

-0.33

POSITIVE LOGITS

 iirc

0.60

 IIRC

0.60

 somewhere

0.55

 someplace

0.53

確か

0.52

somewhere

0.51

 помню

0.50

好像是

0.50

 Somewhere

0.49

 Memor

0.48

Activations Density 0.410%

phrases related to memory recall and uncertainty

first-person hedging and memory-based statements that express uncertainty or tentative belief.

No Comments

No Known Activations