INDEX

Explanations

statements related to events, announcements, and actions taken by organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 myſelf

-0.92

 himſelf

-0.86

 purpoſe

-0.71

 fubject

-0.71

 Monfieur

-0.69

 personlig

-0.67

 myself

-0.66

 personally

-0.66

 personalmente

-0.66

 ſeveral

-0.65

POSITIVE LOGITS

its

1.58

 itself

1.43

Its

1.30

Its

1.26

itself

1.15

its

1.09

 Itself

1.05

它的

0.92

在其

0.81

 яке

0.77

Activations Density 0.680%

statements related to events, announcements, and actions taken by organizations or entities

No Comments

No Known Activations