INDEX

Explanations

terms related to sensory perception and instinct

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

Optim

-0.69

upaten

-0.67

 Grub

-0.65

 pestaña

-0.65

 sério

-0.64

 ISNI

-0.62

 nahilalakip

-0.62

Sunny

-0.62

 Tief

-0.61

θρω

-0.61

POSITIVE LOGITS

 SENSE

1.54

 Sense

1.40

Sense

1.31

sense

1.22

 sense

1.19

 senses

1.15

 sensed

1.15

 Sens

1.13

 SENS

1.11

 Senses

1.11

Activations Density 0.118%

terms related to sensory perception and instinct

No Comments

No Known Activations