INDEX

Explanations

references to political parties and their members, particularly focusing on Democrats and Republicans

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

 defaultstate

-0.97

parsedMessage

-0.82

 saites

-0.82

 onBind

-0.80

 Roskov

-0.77

 للاسماء

-0.74

IsContent

-0.74

WireFormatLite

-0.74

 bezeichneter

-0.72

elemField

-0.70

POSITIVE LOGITS

 Democrats

1.55

 Democrat

1.55

 Democratic

1.44

 Republican

1.32

Democrats

1.27

 Republicans

1.25

Democratic

1.17

Democrat

1.16

 democrats

1.10

 Dems

1.10

Activations Density 0.155%

references to political parties and their members, particularly focusing on Democrats and Republicans

No Comments

No Known Activations