INDEX

Explanations

phrases and contexts involving requests or communication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

WebElementEntity

-0.72

 تضيفلها

-0.64

PreferredItem

-0.62

WireFormatLite

-0.56

RetentionPolicy

-0.55

UserScript

-0.52

PyExc

-0.52

 مشين

-0.52

djangoproject

-0.51

 ComVisible

-0.50

POSITIVE LOGITS

 call

4.24

call

3.78

 Call

3.65

Call

3.64

 calls

3.54

 CALL

3.42

 calling

3.35

CALL

3.23

 Calls

3.14

calls

3.11

Activations Density 0.456%

phrases and contexts involving requests or communication details

No Comments

No Known Activations