INDEX

Explanations

references to dualities or contrasting concepts

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

you can

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

ErrUnexpectedEOF

-0.66

 propOrder

-0.58

 kaarangay

-0.57

SharedDtor

-0.56

verwijspagina

-0.55

styleType

-0.53

 Савезне

-0.53

Autoritní

-0.53

 Administrativna

-0.52

Vidite

-0.50

POSITIVE LOGITS

 tenemos

1.00

we

0.89

 temos

0.88

 Tenemos

0.77

 avem

0.73

Tenemos

0.69

 mamy

0.69

you

0.69

 έχ

0.64

 máme

0.61

Activations Density 0.101%

references to dualities or contrasting concepts

you can

No Comments

No Known Activations