INDEX

Explanations

references to locations or the presence of something 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Monty

-0.65

 ramo

-0.65

dom

-0.65

enzo

-0.63

 Gaff

-0.62

epik

-0.61

stasia

-0.61

 ramos

-0.59

nbsp

-0.59

 MacLeod

-0.59

POSITIVE LOGITS

 THERE

1.01

 there

1.00

there

0.95

 frattempo

0.83

存于互联网档案馆

0.81

 CreateTagHelper

0.81

 berdua

0.80

 дописавши

0.79

 Allí

0.78

 mesmos

0.78

Activations Density 0.072%

references to locations or the presence of something in a narrative

No Comments

No Known Activations