INDEX

Explanations

references to the heart in various contexts, including medical and emotional terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

OGS

-0.90

 nahilalakip

-0.89

soever

-0.83

enderror

-0.82

 linkovi

-0.81

 Roskov

-0.80

 partij

-0.80

URLException

-0.79

 Clapton

-0.79

ungguhnya

-0.77

POSITIVE LOGITS

 HEART

1.72

 heart

1.64

 Heart

1.63

 hearts

1.55

HEART

1.44

 Hearts

1.44

Heart

1.43

heart

1.43

Hearts

1.32

hearts

1.32

Activations Density 0.066%

references to the heart in various contexts, including medical and emotional terms

No Comments

No Known Activations