INDEX

Explanations

content related to personal experiences and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.58

 >=",

-0.58

UnusedPrivate

-0.57

TestingModule

-0.55

transQ

-0.55

хьтан

-0.55

StructEnd

-0.53

 otomatig

-0.51

ManagedBean

-0.49

 purtroppo

-0.48

POSITIVE LOGITS

 person

0.69

ISupport

0.61

 }}"></

0.59

why

0.58

why

0.58

 things

0.57

 gekozen

0.57

 qualcosa

0.57

 facts

0.56

 gewä

0.56

Activations Density 0.367%

content related to personal experiences and values

No Comments

No Known Activations