INDEX

Explanations

trends or patterns in numerical or quantitative data, particularly those involving hashtag symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Personendaten

-0.80

 initComponents

-0.75

 continúas

-0.73

InitVars

-0.67

exitRule

-0.66

 onCreateView

-0.65

SequentialGroup

-0.65

 actionMode

-0.65

 mijne

-0.65

出版年

-0.64

POSITIVE LOGITS

0.54

0.52

\#

0.46

.#

0.46

#[

0.45

!#

0.45

[#

0.42

#$

0.42

'#

0.42

:#

0.42

Activations Density 0.001%

trends or patterns in numerical or quantitative data, particularly those involving hashtag symbols

No Comments

No Known Activations