INDEX

Explanations

references to historical or cultural landmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

UserScript

-0.54

ISupport

-0.51

)}</

-0.47

 offenbar

-0.47

endphp

-0.45

 effectivement

-0.44

řejmě

-0.44

Вариант

-0.44

bibinfo

-0.44

)]=

-0.44

POSITIVE LOGITS

LookAnd

0.87

djangoproject

0.60

uxxxx

0.59

FilterChain

0.58

hiran

0.58

 pinulongan

0.57

 uovo

0.56

 distributes

0.56

Hentet

0.56

 GoogleFonts

0.56

Activations Density 0.153%

references to historical or cultural landmarks

No Comments

No Known Activations