INDEX

Explanations

references to specific events or situations that elicit emotional responses

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

"idea" or a synonym

np_acts-logits-general · gemini-2.0-flash

idea or concept

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

istoitu

-0.58

 CURIAM

-0.56

drawSprites

-0.56

GenerationType

-0.56

 مشين

-0.54

 OFDb

-0.53

 Allociné

-0.51

 '\\;'

-0.51

ANDUM

-0.50

 gepubliceerd

-0.50

POSITIVE LOGITS

 idea

2.68

idea

2.05

 notion

1.98

idée

1.97

 idée

1.95

 concept

1.89

 Idea

1.88

Idea

1.81

 ideia

1.79

 prospect

1.77

Activations Density 0.346%

references to specific events or situations that elicit emotional responses

"idea" or a synonym

idea or concept

No Comments

No Known Activations