INDEX

Explanations

references to various types of services being offered

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

services for

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

<bos>

-0.85

big

-0.48

 large

-0.47

pop

-0.44

 bolt

-0.43

up

-0.40

 heavy

-0.40

make

-0.39

 double

-0.39

 compagn

-0.39

POSITIVE LOGITS

 Services

1.03

 SERVICES

0.96

 services

0.93

SERVICES

0.93

Services

0.93

ervices

0.91

services

0.84

 للاسماء

0.79

 diensten

0.77

 serviços

0.73

Activations Density 0.009%

references to various types of services being offered

services for

No Comments

No Known Activations