INDEX

Explanations

programming-related keywords and terminology, especially those associated with string manipulation and character handling

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

Deals with characters and strings

np_acts-logits-general · gemini-2.0-flash

string character access

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.60

期刊论文

-0.58

الحياه

-0.54

 utafitiHapana

-0.52

enumii

-0.51

fitriones

-0.49

UseVisualStyle

-0.48

 kapturem

-0.47

ToTable

-0.47

IBOutlet

-0.45

POSITIVE LOGITS

NOPQRST

0.62

fromCharCode

0.60

toCharArray

0.55

 letters

0.52

charAt

0.49

 letter

0.46

minLength

0.46

letters

0.45

 Letters

0.45

 huruf

0.45

Activations Density 0.422%

programming-related keywords and terminology, especially those associated with string manipulation and character handling

Deals with characters and strings

string character access

No Comments

No Known Activations