INDEX

Explanations

functions related to parsing integers and floating-point numbers in code

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

parsing numeric strings

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

Билгалдахарш

-0.77

 createState

-0.63

 שוליים

-0.60

ⓧ

-0.59

<bos>

-0.59

Slf

-0.54

EGL

-0.53

 esternos

-0.51

StructEnd

-0.50

writerow

-0.49

POSITIVE LOGITS

parseInt

1.12

 parseInt

1.05

 parseFloat

0.61

parseFloat

0.60

 parseFrom

0.57

parseLong

0.53

 gedeelte

0.48

 Larson

0.47

 tantôt

0.47

parse

0.46

Activations Density 0.002%

functions related to parsing integers and floating-point numbers in code

parsing numeric strings

No Comments

No Known Activations