INDEX

Explanations

references to students and their experiences

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

"student"

np_acts-logits-general · gemini-2.0-flash

student learning, portfolios, roles

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

bootstrapcdn

-0.76

ய்ய

-0.72

 Obamacare

-0.71

]';

-0.71

splitlines

-0.69

 Sykes

-0.68

>),

-0.67

')";

-0.66

__.__

-0.66

ịp

-0.65

POSITIVE LOGITS

 students

1.32

 Students

1.25

students

1.19

Students

1.16

 STUDENTS

1.06

 Student

1.05

STUDENT

1.05

 STUDENT

0.99

Student

0.99

 student

0.97

Activations Density 0.065%

references to students and their experiences

"student"

student learning, portfolios, roles

No Comments

No Known Activations