INDEX

Explanations

expressions related to programming and logic statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

GraphicsUnit

-1.07

 TextInputType

-1.03

 Мексичка

-1.00

 AssemblyCompany

-0.98

EDEFAULT

-0.97

webElementXpaths

-0.92

 pinulongan

-0.92

 Normdatei

-0.92

ScopeManager

-0.89

RegistryLite

-0.89

POSITIVE LOGITS

andExpect

0.64

isContained

0.57

0.54

0.51

tida

0.50

0.49

ra

0.48

 Tech

0.47

0.46

Activations Density 0.030%

expressions related to programming and logic statements

No Comments

No Known Activations