INDEX

Explanations

references to companies' operational changes and updates

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

BeginInit

-0.53

 hänen

-0.50

私が

-0.50

彼が

-0.49

 pribadi

-0.49

companies

-0.48

 мной

-0.47

Companies

-0.47

 argint

-0.47

はじめに

-0.47

POSITIVE LOGITS

its

1.68

Its

1.18

Its

1.14

 svých

1.14

 своих

1.12

 their

1.12

 itself

1.09

 ihren

1.05

 ihre

1.03

 swoich

1.02

Activations Density 0.812%

references to companies' operational changes and updates

No Comments

No Known Activations