INDEX

Explanations

requests or inquiries for specific items or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 jspb

-0.70

 vettore

-0.68

/**

-0.67

noinspection

-0.64

 mourut

-0.63

TypedDataSet

-0.62

TSS

-0.62

 Lleg

-0.62

 esternos

-0.61

érature

-0.61

POSITIVE LOGITS

 looking

0.98

 Looking

0.83

 going

0.82

 LOOKING

0.79

 trying

0.77

 оригіналу

0.71

 really

0.71

Looking

0.70

 Trying

0.70

 thinking

0.70

Activations Density 0.164%

requests or inquiries for specific items or experiences

No Comments

No Known Activations