INDEX

Explanations

concepts related to definitions and principles

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

Follows "principle" or "definition"

np_acts-logits-general · gemini-2.0-flash

definition and principle

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

tlere

-0.38

IUrlHelper

-0.38

 Ueber

-0.37

뀔

-0.35

 propOrder

-0.35

خبر

-0.34

 dispuesto

-0.34

|/

-0.34

便

-0.33

ætte

-0.33

POSITIVE LOGITS

eraard

0.69

czywiście

0.63

sätzlich

0.60

 prosím

0.59

ivably

0.59

verständlich

0.59

ArgsConstructor

0.57

 الحره

0.57

uramente

0.56

šinou

0.55

Activations Density 0.785%

concepts related to definitions and principles

Follows "principle" or "definition"

definition and principle

No Comments

No Known Activations