INDEX

Explanations

occurrences of bracketed notation commonly used in coding or documentation

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

assembly and doc documentation

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

-0.47

ys

-0.45

se

-0.43

si

-0.41

 double

-0.40

↵

-0.40

-0.39

im

-0.39

POSITIVE LOGITS

 EconPapers

0.79

tagHelperRunner

0.78

 autorytatywna

0.76

 الحره

0.72

rungsseite

0.70

Искәрмәләр

0.69

 للمعارف

0.69

 CreateTagHelper

0.69

httphttps

0.67

 незавершена

0.66

Activations Density 0.002%

occurrences of bracketed notation commonly used in coding or documentation

assembly and doc documentation

No Comments

No Known Activations