INDEX

Explanations

statements related to observations and noticing details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Bowles

-0.64

Bag

-0.64

спубли

-0.58

alom

-0.58

 Schulte

-0.57

Mor

-0.57

tbx

-0.57

 Eber

-0.56

thio

-0.56

-0.55

POSITIVE LOGITS

 noticed

1.63

 Notice

1.51

 notice

1.49

 noticing

1.47

 notices

1.46

 NOTICE

1.46

Notice

1.45

noticed

1.45

notice

1.40

 Notices

1.39

Activations Density 0.108%

statements related to observations and noticing details

No Comments

No Known Activations