INDEX

Explanations

references to students in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

="/">

-0.61

(;;)

-0.58

HEIM

-0.56

!("{}",

-0.55

깥

-0.54

Demografia

-0.54

нились

-0.54

 inversely

-0.53

%,

-0.53

 Manufacturer

-0.53

POSITIVE LOGITS

 students

3.43

 student

3.33

student

3.08

 Students

3.07

students

3.05

Students

2.99

 Student

2.96

Student

2.85

 STUDENT

2.76

 STUDENTS

2.65

Activations Density 0.195%

references to students in various contexts

No Comments

No Known Activations