INDEX

Explanations

statements reflecting opinions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Portail

-0.84

 pinulongan

-0.66

ReusableCell

-0.62

GEBURTSDATUM

-0.62

Cyfeiriadau

-0.59

 AssemblyVersion

-0.58

AnimationsModule

-0.57

ftagPool

-0.57

KURZBESCHREIBUNG

-0.56

 Roskov

-0.56

POSITIVE LOGITS

setVerticalGroup

0.67

ContentAlignment

0.60

omiast

0.56

ihnachts

0.53

uggest

0.53

 postIndex

0.52

 Quindi

0.52

 bezeichneter

0.51

втра

0.51

ślę

0.51

Activations Density 0.067%

statements reflecting opinions or sentiments

No Comments

No Known Activations