INDEX

Explanations

expressions of personal identity and sentiments related to being introverted or a fan of something

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

 vérit

-0.63

 mourut

-0.62

 möjlighet

-0.61

 verticales

-0.61

 navideñas

-0.58

UseVisualStyle

-0.56

 duele

-0.56

 gezet

-0.56

 coloridas

-0.55

 vägen

-0.55

POSITIVE LOGITS

 pinulongan

0.68

)*/

0.62

PMailer

0.60

 Extre

0.60

(");

0.59

)");

0.59

 betweenstory

0.59

createCanvas

0.58

DebuggerNonUser

0.58

########.

0.56

Activations Density 0.241%

expressions of personal identity and sentiments related to being introverted or a fan of something

No Comments

No Known Activations