INDEX

Explanations

elements related to health interventions and outcomes

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

"goal" or similar objective

np_acts-logits-general · gemini-2.0-flash

setting goals

np_acts-logits-general · gemini-2.5-flash-lite

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

 виправивши

-0.74

ніципа

-0.63

 utafitiHapana

-0.63

ंदीखरीदारी

-0.56

AccessorTable

-0.54

पया

-0.50

ItemLayout

-0.50

dbury

-0.50

ThemeOverlay

-0.50

 Walkover

-0.48

POSITIVE LOGITS

 goals

2.53

 goal

2.35

 Goals

2.19

Goals

2.11

goals

2.10

goal

2.09

 objectives

2.09

 Goal

2.02

Goal

1.97

 targets

1.95

Activations Density 0.393%

elements related to health interventions and outcomes

"goal" or similar objective

setting goals

No Comments

No Known Activations