INDEX

Explanations

references to specific names or individuals in a context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

BeginContext

-0.82

WaitGroup

-0.69

 المعيارى

-0.68

KEYCODE

-0.67

 jScrollPane

-0.66

 BoxFit

-0.66

 GenerationType

-0.64

principalColumn

-0.64

 HasFactory

-0.63

 виправивши

-0.63

POSITIVE LOGITS

 designer

0.76

 fashion

0.65

 boutique

0.64

 bohemian

0.62

 boutiques

0.61

 brands

0.60

 brand

0.60

ollection

0.58

 designers

0.57

 creative

0.57

Activations Density 0.060%

references to specific names or individuals in a context

No Comments

No Known Activations