INDEX

Explanations

references to mission-driven activities or efforts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Monfieur

-0.94

 myſelf

-0.88

 pleaſure

-0.86

 ſind

-0.84

 Jefus

-0.82

 houſe

-0.82

 Theſe

-0.80

<unused41>

-0.80

 ſche

-0.79

<unused17>

-0.79

POSITIVE LOGITS

 mission

0.77

Mission

0.69

 Mission

0.66

 missions

0.66

mission

0.63

 misiones

0.60

 MISSION

0.59

 współpracy

0.56

MISSION

0.56

 misión

0.50

Activations Density 0.253%

references to mission-driven activities or efforts

No Comments

No Known Activations