INDEX

Explanations

programming-related keywords and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

urally

-0.73

 estekak

-0.69

зулта

-0.67

клопе

-0.66

 HasFactory

-0.66

newArrayList

-0.65

surate

-0.65

 StringTokenizer

-0.64

createCanvas

-0.63

Personendaten

-0.61

POSITIVE LOGITS

until

0.62

model

0.58

pojo

0.52

constant

0.52

service

0.52

entity

0.51

 constant

0.50

Until

0.48

dao

0.47

bean

0.47

Activations Density 0.045%

programming-related keywords and class definitions

No Comments

No Known Activations