INDEX

Explanations

specific scientific terms related to experimental procedures and results

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

seeding, modification, chart, recognition

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

 nakalista

-0.58

Enllaces

-0.57

 tiguan

-0.56

 microbiome

-0.54

новниш

-0.52

 curation

-0.51

 BrowserModule

-0.51

 CrossFit

-0.50

 sustainability

-0.50

 snipers

-0.49

POSITIVE LOGITS

 Италијани

0.46

AsUp

0.46

 BoxFit

0.44

mogat

0.43

COUVER

0.42

RTEE

0.40

ératures

0.38

tagHelperRunner

0.36

 Rhodesia

0.36

 ferons

0.36

Activations Density 0.572%

specific scientific terms related to experimental procedures and results

seeding, modification, chart, recognition

No Comments

No Known Activations