INDEX

Explanations

negative aspects related to personal experiences and evaluations of design or choices

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

 auffi

-1.48

Efq

-1.46

 myſelf

-1.41

 ſtate

-1.39

 houſe

-1.35

 Monfieur

-1.35

 perſon

-1.34

 Jefus

-1.32

 ſta

-1.28

 ſeveral

-1.27

POSITIVE LOGITS

0.55

0.54

0.50

0.47

 thành

0.44

Pri

0.43

Activations Density 0.336%

negative aspects related to personal experiences and evaluations of design or choices

No Comments

No Known Activations