INDEX

Explanations

references to legal cases or court rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

offee

-0.60

Bae

-0.54

Bae

-0.53

Климат

-0.53

 épaules

-0.53

envoy

-0.53

 Σε

-0.51

országban

-0.50

rítica

-0.50

rawDesc

-0.50

POSITIVE LOGITS

 ModelExpression

0.71

 AssemblyCulture

0.70

 MotionEvent

0.69

évaluateur

0.67

PreferredItem

0.66

WebElementEntity

0.63

hartt

0.60

 CreateTagHelper

0.60

dataclass

0.58

 يتيمه

0.57

Activations Density 1.393%

references to legal cases or court rulings

No Comments

No Known Activations