INDEX

Explanations

associations related to positive and negative values and their representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

TagMode

-0.63

Jîn

-0.62

EndGlobalSection

-0.61

onuc

-0.60

 âgé

-0.58

 AssemblyVersion

-0.56

Personensuche

-0.55

ijoje

-0.55

 näm

-0.54

ffindor

-0.54

POSITIVE LOGITS

則是

1.44

则是

1.34

 ditto

1.29

則

1.15

ditto

1.11

则

1.11

 conversely

1.08

 sebaliknya

1.07

 наоборот

1.07

 thereafter

1.04

Activations Density 1.502%

associations related to positive and negative values and their representations

No Comments

No Known Activations