INDEX

Explanations

names of individuals and institutions related to cultural or medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 caviar

-0.52

Mej

-0.47

 Tobago

-0.46

 forKey

-0.46

πως

-0.45

 fuoco

-0.45

 Référence

-0.44

AddWithValue

-0.44

 Winfield

-0.42

 framför

-0.42

POSITIVE LOGITS

 Karnataka

0.95

 Bengaluru

0.88

 Kannada

0.83

UnusedPrivate

0.81

 Bangalore

0.77

Karn

0.74

 Mysore

0.74

calaure

0.68

новниш

0.68

lossians

0.68

Activations Density 0.111%

names of individuals and institutions related to cultural or medical contexts

No Comments

No Known Activations