INDEX

Explanations

references to the United States and related geographical or political concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

Personendaten

-0.91

 StatefulWidget

-0.87

 StatelessWidget

-0.85

 насељу

-0.81

ThroughAttribute

-0.78



-0.78

StoryboardSegue

-0.77

Autoritní

-0.75

#+#

-0.72

PerformLayout

-0.72

POSITIVE LOGITS

Климат

0.52

apyrus

0.46

 secas

0.45

 sén

0.45

 sensazione

0.44

sterious

0.44

ropra

0.44

 democracia

0.43

Extrait

0.43

 fiducia

0.43

Activations Density 0.149%

references to the United States and related geographical or political concepts

No Comments

No Known Activations