INDEX

Explanations

functions and variables related to parsing and manipulating numerical values in a programming context

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

`<start_of_turn>user`

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

verifyException

-0.64

Autoritní

-0.63

NumberFormat

-0.63

GHIJKLM

-0.59

 protoimpl

-0.59

mybatisplus

-0.58

новништво

-0.57

imageshack

-0.55

Читати

-0.54

AutoField

-0.53

POSITIVE LOGITS

CGFloat

1.02

parseFloat

0.96

 parseFloat

0.88

CGSize

0.75

innerHeight

0.65

CGPoint

0.62

getBounding

0.54

offsetHeight

0.52

clientHeight

0.47

keyframes

0.40

Activations Density 0.001%

functions and variables related to parsing and manipulating numerical values in a programming context

`<start_of_turn>user`

No Comments

No Known Activations