INDEX

Explanations

code-related keywords and declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 originaux

-0.58

 financières

-0.54

 mineures

-0.51

 sää

-0.50

 kirja

-0.49

 gratuites

-0.47

 pasirink

-0.47

 aikaa

-0.45

цездатний

-0.45

 Omen

-0.45

POSITIVE LOGITS

 initComponents

0.85

expandindo

0.77

 static

0.75

**/

0.72

Vidite

0.70

Clik

0.66

')):

0.65

CppMethod

0.64

 '+':

0.64

MemoryWarning

0.63

Activations Density 0.023%

code-related keywords and declarations

No Comments

No Known Activations