INDEX

Explanations

structured data format indicators and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ClientRect

-0.53

خاذ

-0.47

_^

-0.46

แห่ง

-0.45

 Professional

-0.45

Professional

-0.45

 externi

-0.44

ménage

-0.44

 Wray

-0.44

 بیر

-0.44

POSITIVE LOGITS

 notice

0.57

TestClass

0.57

 snippetHide

0.54

oredCriteria

0.52

TextWatcher

0.50

UnitTesting

0.50

BD

0.50

 onResponse

0.49

 Notice

0.48

 documenta

0.47

Activations Density 0.146%

structured data format indicators and references

No Comments

No Known Activations