INDEX

Explanations

variations of the word "total" and its related forms

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

totality or tot combinations

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Merz

-0.56

Mě

-0.54

 Impedance

-0.54

ברס

-0.52

 Mercier

-0.51

 Irlanda

-0.51

 Guitar

-0.51

 Auditing

-0.49

Legături

-0.48

Amigo

-0.48

POSITIVE LOGITS

tot

1.77

tot

1.54

Tot

1.53

Tot

1.53

TOT

1.09

TOT

1.03

 tots

0.79

ImageContext

0.77

 totality

0.65

STOT

0.60

Activations Density 0.029%

variations of the word "total" and its related forms

totality or tot combinations

No Comments

No Known Activations