INDEX

Explanations

questions that inquire about methods, processes, or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

tvguidetime

-0.91

AndEndTag

-0.89

 initComponents

-0.89

 Theſe

-0.88

Efq

-0.87

 myſelf

-0.86

 itſelf

-0.84

 ویکی‌پدیا

-0.83

 poffible

-0.82

WithIOException

-0.79

POSITIVE LOGITS

How

1.52

 What

1.42

Why

1.41

How

1.38

Why

1.28

Who

1.24

Is

1.24

What

1.22

Is

1.19

Who

1.16

Activations Density 0.190%

questions that inquire about methods, processes, or evaluations

No Comments

No Known Activations