INDEX

Explanations

sentiment related to positive experiences or opinions

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

describing positive attributes

np_acts-logits-general · gemini-2.0-flash

descriptive adjectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

BASEPATH

-0.57

 Suppression

-0.44

 Unable

-0.42

 Readiness

-0.41

 remuneration

-0.41

 fons

-0.40

 ragaz

-0.40

 empe

-0.40

 Utilization

-0.39

 goda

-0.39

POSITIVE LOGITS

 sharp

0.59

 robust

0.57

 sleek

0.57

 compact

0.56

 flexible

0.56

 colourful

0.55

 rugged

0.55

 elegant

0.54

 extremely

0.54

 concise

0.54

Activations Density 0.754%

sentiment related to positive experiences or opinions

describing positive attributes

descriptive adjectives

No Comments

No Known Activations