INDEX

Explanations

programming-related syntax, particularly focused on data types and numerical values

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

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

Personendaten

-0.59

 ſch

-0.56

GOTREF

-0.55

majánló

-0.55

 mxArray

-0.54

tagHelperRunner

-0.54

 BoxDecoration

-0.53

 myſelf

-0.52

ThroughAttribute

-0.52

ſelves

-0.52

POSITIVE LOGITS

parseInt

0.64

IntegerField

0.63

putInt

0.56

 integer

0.55

Integer

0.54

 Integer

0.54

strconv

0.53

 iload

0.52

GetInt

0.52

 parseInt

0.52

Activations Density 0.670%

programming-related syntax, particularly focused on data types and numerical values

No Comments

No Known Activations