INDEX

Explanations

concepts related to emotional depth and individual experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 houſe

-1.00

 myſelf

-0.95

 Houſe

-0.90

 Monfieur

-0.89

Efq

-0.89

 Shakspeare

-0.87

 Jefus

-0.86

 reaſon

-0.85

 uſe

-0.84

 purpoſe

-0.84

POSITIVE LOGITS

sense

0.56

+#+

0.56

Linki

0.53

 sense

0.49

 grand

0.48

ex

0.47

了一种

0.47

>);

0.47

und

0.46

Сылтамалар

0.46

Activations Density 0.319%

concepts related to emotional depth and individual experiences

No Comments

No Known Activations