INDEX

Explanations

instances of the word "jump" and its variations in various contexts

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

 sufficiente

-0.71

 policiers

-0.61

 Paulson

-0.60

 πως

-0.59

olato

-0.59

 Snyder

-0.58

Canal

-0.58

 Britton

-0.57

 فإن

-0.57

Roh

-0.56

POSITIVE LOGITS

 jump

1.87

 Jump

1.86

 JUMP

1.83

 jumps

1.77

jump

1.72

Jump

1.69

JUMP

1.62

 jumping

1.57

 Leap

1.56

 jumped

1.55

Activations Density 0.071%

instances of the word "jump" and its variations in various contexts

No Comments

No Known Activations