INDEX

Explanations

symbols and formatting elements within 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 @ 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

 Taktlose

-0.39

 verste

-0.35

UnsafeEnabled

-0.34

ganu

-0.34

 Galloway

-0.34

:])

-0.34

rdata

-0.33

 مدن

-0.33

 fairy

-0.33

 sand

-0.33

POSITIVE LOGITS

MigrationBuilder

0.65

UnusedPrivate

0.57

exitRule

0.56

PerformLayout

0.54

UserScript

0.52

 useRef

0.51

SaveChangesAsync

0.50

 chi̍t

0.50

AndroidJUnit

0.50

 يتيمه

0.50

Activations Density 0.016%

symbols and formatting elements within text

No Comments

No Known Activations