INDEX

Explanations

references to learning and lessons

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 doInBackground

-0.83

WebElementEntity

-0.78

Varint

-0.75

awtextra

-0.73

PROPOSED

-0.73

 nahilalakip

-0.71

LabelTagHelper

-0.70

sendRedirect

-0.69

cemment

-0.67

 BoxFit

-0.67

POSITIVE LOGITS

 learned

1.81

learned

1.67

 Learned

1.44

 lessons

1.30

 taught

1.29

 learnt

1.27

taught

1.13

 Lessons

1.11

 aprendido

1.08

lessons

1.05

Activations Density 0.115%

references to learning and lessons

No Comments

No Known Activations