INDEX

Explanations

references to Canadian television networks and their programming

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

Follows a proper noun

np_acts-logits-general · gemini-2.0-flash

Canadian media and institutions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 recognised

-0.81

 minimise

-0.80

Whilst

-0.80

 maximise

-0.80

 summarise

-0.80

 specialises

-0.78

 standardised

-0.77

 optimise

-0.77

 recognises

-0.77

 utilising

-0.76

POSITIVE LOGITS

SharedDtor

0.95

 BoxDecoration

0.74

 ſeveral

0.72

DockStyle

0.72

 pleaſure

0.70

цездатний

0.70

 himſelf

0.69

 themſelves

0.68

Efq

0.65

ButterKnife

0.64

Activations Density 0.083%

references to Canadian television networks and their programming

Follows a proper noun

Canadian media and institutions

No Comments

No Known Activations