INDEX

Explanations

code-related terms and references to object-oriented programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vidite

-0.83

theless

-0.75

tvguidetime

-0.73

 NavController

-0.72

Autoritní

-0.71

fjspx

-0.69

dsi

-0.68

Personendaten

-0.68

PhysRevLett

-0.67

 Ceramby

-0.66

POSITIVE LOGITS

[]

0.61

[]:

0.61

addContainerGap

0.59

localObject

0.54

rxjs

0.52

ärä

0.52

callable

0.52

 član

0.52

 Quincy

0.49

 vật

0.49

Activations Density 0.031%

code-related terms and references to object-oriented programming concepts

No Comments

No Known Activations