INDEX

Explanations

actions and evaluative processes related to assessment and decision-making

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

discusses or asserts a fact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Lul

-0.45

WL

-0.39

Pal

-0.38

pal

-0.37

pal

-0.37

書館

-0.36

Wod

-0.36

彤

-0.35

pet

-0.35

 métier

-0.35

POSITIVE LOGITS

 lisäksi

0.66

fjspx

0.63

 dessutom

0.59

 également

0.58

 gärna

0.56

 ayrıca

0.56

 eventuali

0.55

脚注の使い方

0.54

 myös

0.53

Cyfarwyddwr

0.53

Activations Density 0.106%

actions and evaluative processes related to assessment and decision-making

discusses or asserts a fact

No Comments

No Known Activations