INDEX

Explanations

comparisons related to quantifiable data or significant figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

давно

-0.46

②

-0.45

 adanya

-0.42

ждую

-0.42

那天

-0.41

 trouvent

-0.41

 egyes

-0.40

которые

-0.39

isEnd

-0.38

ultima

-0.38

POSITIVE LOGITS

 approximately

1.04

 roughly

0.97

 approx

0.96

 approxim

0.95

noin

0.90

approximately

0.87

 amount

0.87

 approximate

0.85

 Approx

0.85

 MainAxisSize

0.85

Activations Density 0.430%

comparisons related to quantifiable data or significant figures

No Comments

No Known Activations