INDEX

Explanations

interrogative words that pertain to questions of understanding and causation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

UnusedPrivate

-0.73

twimg

-0.62

msgTypes

-0.62

 كومونز

-0.62

atrième

-0.58

 jsPsych

-0.57

CppCodeGen

-0.54

บัติ

-0.53

tonsoft

-0.53

 nahilalakip

-0.52

POSITIVE LOGITS

why

1.36

why

1.32

WHY

1.21

WHY

1.16

where

1.15

how

1.14

HOW

1.14

Why

1.13

how

1.13

Why

1.10

Activations Density 0.182%

interrogative words that pertain to questions of understanding and causation

No Comments

No Known Activations

interrogative words that pertain to questions of understanding and causation

No Comments

No Known Activations