INDEX

Explanations

instances and variations of the word "act" and its related forms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Marconi

-0.84

 Latimer

-0.80

erequisite

-0.80

তথ্যসূত্র

-0.76

sonian

-0.76

 Brewster

-0.76

 Einer

-0.75

 gera

-0.74

SGS

-0.74

TopLevel

-0.74

POSITIVE LOGITS

ACT

1.57

act

1.57

Act

1.53

 acts

1.50

 Acts

1.49

Act

1.28

Acts

1.25

ACT

1.23

 ACTS

1.19

 Acton

1.19

Activations Density 0.081%

instances and variations of the word "act" and its related forms in various contexts

No Comments

No Known Activations