INDEX

Explanations

`less than` and `greater than` symbols or other XML-style tags and attributes

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

StructEnd

-0.67

 betweenstory

-0.63

Попис

-0.62

 SwitchCompat

-0.60

 '\\;'

-0.59

 himo

-0.59

transQ

-0.59

 MaterialApp

-0.58

ArrowToggle

-0.58

icksburg

-0.57

POSITIVE LOGITS

 IBOutlet

0.81

Hozzáférés

0.65

 reason

0.64

 Silber

0.62

 wrong

0.59

ाले

0.58

ⓧ

0.58

 desire

0.57

 concern

0.52

Activations Density 0.005%

`less than` and `greater than` symbols or other XML-style tags and attributes

No Comments

No Known Activations