INDEX

Explanations

references to user interface components and design elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

LayoutStyle

-0.52

-0.48

."

-0.46

↵↵

-0.46

presto

-0.45

principalTable

-0.45

<th>

-0.45

Jeografia

-0.43

POSITIVE LOGITS

 myſelf

0.95

 pleaſure

0.85

 houſe

0.84

 itſelf

0.81

 ſeveral

0.80

 Jefus

0.78

 ſmall

0.78

 himſelf

0.76

Efq

0.76

 purpoſe

0.75

Activations Density 0.030%

references to user interface components and design elements

No Comments

No Known Activations