INDEX

Explanations

technical jargon and programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

EndGlobalSection

-0.64

amazonaws

-0.59

createCanvas

-0.53

 Мексичка

-0.52

endcsname

-0.51

BufferException

-0.51

PutMapping

-0.50

 AttributeSet

-0.48

ingtones

-0.48

putExtra

-0.48

POSITIVE LOGITS

 Belén

0.58

:])

0.58

+#+#

0.58

 متعلقه

0.57

ore

0.57

>{"

0.57

 problematic

0.57

 تضيفلها

0.57

ecap

0.57

Begriffsklä

0.56

Activations Density 1.579%

technical jargon and programming-related terms

No Comments

No Known Activations