INDEX

Explanations

import statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

LookAnd

-0.89

 itſelf

-0.67

 flèche

-0.61

цездатний

-0.60

invokeLater

-0.59

 архивлан

-0.57

JspWriter

-0.57

 unknownFields

-0.56

IonicModule

-0.56

queryInterface

-0.54

POSITIVE LOGITS

MENAFN

0.87

 IndexPath

0.65

PREFERRED

0.62

enumi

0.62

 useContext

0.61

 forKey

0.60

?}",

0.58

qtype

0.58

chables

0.57

 isKindOfClass

0.57

Activations Density 0.012%

import statements in code

No Comments

No Known Activations