INDEX

Explanations

instances of the word "strike."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 initComponents

-0.48

 Ideen

-0.41

 continuum

-0.40

 atve

-0.40

 Wikiseite

-0.39

 Vorstellung

-0.39

 Zusch

-0.38

/**

-0.36

 hắn

-0.36

 pelan

-0.36

POSITIVE LOGITS

 strike

1.15

strike

1.04

Strike

1.02

 Strike

1.00

 strikes

0.96

 struck

0.91

 Strikes

0.86

 striking

0.78

 Striking

0.71

 kasarigan

0.61

Activations Density 0.105%

instances of the word "strike."

No Comments

No Known Activations