INDEX

Explanations

terms related to measurements and specifications in scientific contexts

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

citations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ագրություններ

-0.60

enumii

-0.56

enumi

-0.56

جغرافيا

-0.53

 AssemblyCulture

-0.53

 tartalomajánló

-0.52

Rtl

-0.50

 HttpNotFound

-0.49

expandindo

-0.48

Tembelea

-0.47

POSITIVE LOGITS

 跳转至

0.60

Przypisy

0.59

Linki

0.45

 esquecer

0.43

 resourceCulture

0.43

arrivo

0.43

 referenties

0.43

 réglable

0.42

Παραπομπές

0.42

CloseOperation

0.41

Activations Density 0.220%

terms related to measurements and specifications in scientific contexts

citations and references

No Comments

No Known Activations