INDEX

Explanations

terms related to cognitive processes and attention in experimental settings

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

Preceding punctuation (periods, commas, parentheses)

np_acts-logits-general · gemini-2.0-flash

psychology experiments and research terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

 aimé

-0.50

 Risk

-0.48

 personaggio

-0.48

üe

-0.48

Risk

-0.47

 Union

-0.46

SpringRunner

-0.45

emar

-0.45

тет

-0.44

dra

-0.44

POSITIVE LOGITS

 jsPsych

1.03

MigrationBuilder

0.88

 propOrder

0.87

 betweenstory

0.87

 psychologists

0.83

aarrggbb

0.80

ScopeManager

0.78

Personendaten

0.73

 Psychol

0.72

 Baillargeon

0.69

Activations Density 1.549%

terms related to cognitive processes and attention in experimental settings

Preceding punctuation (periods, commas, parentheses)

psychology experiments and research terms

No Comments

No Known Activations