INDEX

Explanations

references to groups or collective instances of items or phenomena

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

-0.45

-0.44

tif

-0.44

 term

-0.43

 over

-0.42

ref

-0.42

Referanser

-0.41

POSITIVE LOGITS

Datuak

0.99

تقاوى

0.95

 Theſe

0.92

MessageOf

0.85

Personendaten

0.83

BufferException

0.80

 MainAxisSize

0.78

TargetException

0.77

 дописавши

0.77

rrggbb

0.76

Activations Density 0.731%

references to groups or collective instances of items or phenomena

No Comments

No Known Activations