INDEX

Explanations

instances of the word "show" and its variations indicating presentation or demonstration

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

demonstrations or indications

np_acts-logits-general · gemini-2.0-flash

showing or indicating

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

Климат

-0.52

ucap

-0.47

yntaxException

-0.45

Witam

-0.44

Nesta

-0.43

guesses

-0.42

clientY

-0.41

 murmured

-0.41

 spørsmål

-0.41

 oración

-0.41

POSITIVE LOGITS

 signs

0.96

 signes

0.88

how

0.88

 Showing

0.86

 Shows

0.85

Showing

0.85

Shows

0.84

showed

0.83

 SIGNS

0.83

shows

0.82

Activations Density 0.158%

instances of the word "show" and its variations indicating presentation or demonstration

demonstrations or indications

showing or indicating

No Comments

No Known Activations