INDEX

Explanations

references to specific characters or entities in a narrative

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

 kasarigan

-0.61

 שוליים

-0.57

 >=",

-0.55

Diwedd

-0.54

endregion

-0.53

 <<<<<<<<<<<<<<

-0.52

 trac

-0.51

aulted

-0.51

Datuak

-0.49

 heat

-0.49

POSITIVE LOGITS

ou

1.91

OU

1.50

ous

1.29

ouc

1.07

ou

1.03

OUS

1.01

Ou

1.01

our

1.00

ouk

0.96

ouse

0.96

Activations Density 1.902%

references to specific characters or entities in a narrative

No Comments

No Known Activations