INDEX

Explanations

terms related to stimulation, initiation, and the invoking of emotional or chemical responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addContainerGap

-0.64

 Koran

-0.56

 arşivlendi

-0.55

roleum

-0.54

Christi

-0.54

 AssemblyCulture

-0.54

 fairing

-0.53

ámide

-0.52

NOL

-0.52

 Nema

-0.52

POSITIVE LOGITS

 triggered

1.23

 triggers

1.13

 trigger

1.11

 triggering

1.07

 Trigger

1.05

Triggers

1.05

 evoked

1.05

 Triggers

1.05

triggers

1.04

triggered

1.02

Activations Density 0.294%

terms related to stimulation, initiation, and the invoking of emotional or chemical responses

No Comments

No Known Activations