INDEX

Explanations

references to DOM (Document Object Model) elements and functions within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

:✨

-0.77

 '\\;'

-0.68

+#+#

-0.65

principalColumn

-0.60

SharedCtor

-0.57

 Diretto

-0.54

Kariera

-0.51

MessageOf

-0.51

 Taktlose

-0.51

pulseira

-0.50

POSITIVE LOGITS

dom

2.53

dom

1.89

Dom

1.77

Dom

1.73

DOM

1.70

doms

1.58

DOM

1.55

edom

1.08

 domes

0.98

idom

0.97

Activations Density 0.038%

references to DOM (Document Object Model) elements and functions within the text

No Comments

No Known Activations