INDEX

Explanations

references to case studies or reports

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

"Case" followed by a preposition or noun

np_acts-logits-general · gemini-2.0-flash

case report, study, or presentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 صوتيه

-0.84

 Theſe

-0.84

yntaxException

-0.80

 Mercurio

-0.80

 Monfieur

-0.78

 diſt

-0.76

ArrowToggle

-0.75

 Administrativna

-0.73

 سكانية

-0.73

 للمعارف

-0.73

POSITIVE LOGITS

 Cases

1.00

Cases

1.00

cases

0.98

 CASE

0.98

 cases

0.97

 Case

0.92

CASE

0.90

 study

0.90

 CASES

0.86

case

0.85

Activations Density 0.148%

references to case studies or reports

"Case" followed by a preposition or noun

case report, study, or presentation

No Comments

No Known Activations