INDEX

Explanations

quantifiable metrics related to capacity or accommodation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Theſe

-1.06

 pleaſure

-1.06

 فريبيس

-1.00

 raiſ

-0.98

 myſelf

-0.98

 Reſ

-0.97

 purpoſe

-0.94

 Jefus

-0.94

 Majefty

-0.93

 theſe

-0.92

POSITIVE LOGITS

can

0.58

Eloquent

0.48

 your

0.45

max

0.45

0.44

 could

0.44

 maximum

0.44

homonymie

0.43

mo

0.43

Activations Density 0.235%

quantifiable metrics related to capacity or accommodation

No Comments

No Known Activations