INDEX

Explanations

numerical data and structural elements

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

Hexadecimal and reference values

np_acts-logits-general · gemini-2.0-flash

academic citations or references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

IVEREF

-0.77

 imprimée

-0.67

mybatisplus

-0.65

 AssemblyCompany

-0.62

 unknownFields

-0.61

 Baillargeon

-0.61

 RSSSF

-0.60

AntiForgeryToken

-0.60

 OMITBAD

-0.60

Dtor

-0.60

POSITIVE LOGITS

enumi

0.65

expandindo

0.61

IContainer

0.53

참고

0.48

Билгалдахарш

0.48

enumii

0.47

spo

0.46

fahrzeug

0.44

ouchable

0.44

Activations Density 0.010%

numerical data and structural elements

Hexadecimal and reference values

academic citations or references

No Comments

No Known Activations