INDEX

Explanations

situations involving companionship and closeness between individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 plankton

-0.46

-0.45

 anonim

-0.45

 Branchen

-0.45

 cono

-0.45

Naissance

-0.44

 Himo

-0.44

alin

-0.44

iwisata

-0.43

 quảng

-0.42

POSITIVE LOGITS

 upstairs

1.07

 downstairs

0.97

 kitchen

0.95

 house

0.89

 bedroom

0.88

 household

0.86

parsedMessage

0.76

bedroom

0.76

household

0.76

 home

0.75

Activations Density 0.507%

situations involving companionship and closeness between individuals

No Comments

No Known Activations