INDEX

Explanations

coding-related terms and functions

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

swift decoder and js

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

 AssemblyProduct

-0.54

切

-0.49

 Inclusive

-0.49

 Cuts

-0.47

 Positions

-0.46

 Jackson

-0.45

WriteTagHelper

-0.45

olari

-0.45

ucap

-0.45

shifts

-0.45

POSITIVE LOGITS

AccessorTable

0.84

tagHelperRunner

0.82

 Roskov

0.81

 beginnetje

0.56

 EconPapers

0.55

 gyhoeddwyd

0.53

Kaynakça

0.53

contentLoaded

0.51

Fordítás

0.51

httphttps

0.50

Activations Density 0.000%

coding-related terms and functions

swift decoder and js

No Comments

No Known Activations