INDEX

Explanations

terms related to mental states and mindfulness practices

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

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

 مشين

-0.63

annica

-0.62

CodeAttribute

-0.60

rungsseite

-0.60

currentColor

-0.59

prefixer

-0.58

ⓘ

-0.58

 recommandée

-0.58

THISDAY

-0.57

FontOfSize

-0.56

POSITIVE LOGITS

 MIND

0.80

lessly

0.78

MIND

0.69

 Mind

0.69

sets

0.67

 minds

0.67

 Minds

0.66

bog

0.63

bog

0.63

клопе

0.60

Activations Density 0.071%

terms related to mental states and mindfulness practices

No Comments

No Known Activations