INDEX

Explanations

references to specific geographical locations and their associated contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Magdalen

-0.92

 Wilma

-0.86

 Pais

-0.85

 Nagel

-0.85

 Carrington

-0.83

 Sjö

-0.83

ագրություններ

-0.82

gamesh

-0.82

 Île

-0.81

 Perci

-0.81

POSITIVE LOGITS

 Kearney

0.83

𝘤

0.74

 Differenz

0.74

 keter

0.74

oporosis

0.73

 Tind

0.71

phorbia

0.71

 partielle

0.70

 kans

0.69

mediate

0.69

Activations Density 2.583%

references to specific geographical locations and their associated contexts

No Comments

No Known Activations