INDEX

Explanations

negations and undesirable outcomes

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

 disponibilités

-0.55

moveToFirst

-0.46

ball

-0.44

<?

-0.42

master

-0.41

 وصلة

-0.41

сем

-0.41

 mitra

-0.40

Ball

-0.40

shafen

-0.38

POSITIVE LOGITS

ChildScrollView

0.73

">—

0.69

PreferredItem

0.69

 الاطلاع

0.67

)");

0.67

IUrlHelper

0.67

RUnlock

0.67

 SearchView

0.66

PRNewswire

0.66

nextProps

0.65

Activations Density 0.698%

negations and undesirable outcomes

No Comments

No Known Activations