INDEX

Explanations

words related to speaking or communication

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

icitis

-0.60

Norma

-0.60

Obrázky

-0.60

 professionali

-0.59

 Norma

-0.58

لينكات

-0.58

MSG

-0.57

łąd

-0.57

felix

-0.56

 umane

-0.56

POSITIVE LOGITS

 spoke

1.01

spoke

1.01

 spokes

0.92

 talked

0.90

 spoken

0.86

Spo

0.82

 Spokes

0.79

SPO

0.79

Spo

0.77

 mention

0.76

Activations Density 0.098%

words related to speaking or communication

No Comments

No Known Activations