INDEX

Explanations

phrases that introduce examples or instances

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

 Monfieur

-0.69

 Majefty

-0.68

 chofe

-0.64

 noires

-0.61

Eſ

-0.61

Efq

-0.58

 uſed

-0.57

 Cæsar

-0.57

 houſe

-0.56

 Jefus

-0.55

POSITIVE LOGITS

 example

0.77

 insuffisamment

0.77

SpringRunner

0.71

 esempio

0.69

 المثال

0.68

 examples

0.67

Enllaces

0.67

 exempel

0.67

etc

0.66

ScopeManager

0.64

Activations Density 0.142%

phrases that introduce examples or instances

No Comments

No Known Activations