INDEX

Explanations

references to legal codes and procedural rules

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

 Réponses

-0.71

abestanden

-0.69

पया

-0.67

setVerticalGroup

-0.65

Tikang

-0.62

expandindo

-0.61

radas

-0.60

andExpect

-0.59

usehen

-0.59

TED

-0.57

POSITIVE LOGITS

contentLoaded

0.54

 tillegg

0.51

 trono

0.49

沿革

0.46

 referirse

0.45

|()

0.45

 chronology

0.43

 numele

0.43

 onPostExecute

0.43

 fortæller

0.43

Activations Density 0.278%

references to legal codes and procedural rules

No Comments

No Known Activations