INDEX

Explanations

phrases related to analysis and examination of ideas or cases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 AssemblyTitle

-1.05

.*")]

-0.73

XMLSchema

-0.70

 noqa

-0.67

 propOrder

-0.67

SBATCH

-0.66

IUrlHelper

-0.63

loài

-0.61

 AssemblyVersion

-0.60

كذا

-0.60

POSITIVE LOGITS

 Betrachtung

0.64

 consider

0.59

 Consider

0.59

 contextual

0.57

consider

0.57

 Betrach

0.56

 consideration

0.55

Consider

0.55

 considerar

0.54

pe

0.53

Activations Density 0.648%

phrases related to analysis and examination of ideas or cases

No Comments

No Known Activations