INDEX

Explanations

terms related to understanding and comprehension

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

番

-0.63

tığı

-0.62

 pick

-0.59

zości

-0.58

 BIBLIO

-0.56

 drop

-0.55

fabs

-0.55

spyOn

-0.54

 PICK

-0.54

ofire

-0.54

POSITIVE LOGITS

 understand

3.48

understand

3.23

 understanding

3.20

 understands

3.17

 Understand

3.17

 understood

3.09

Understand

3.07

understanding

2.96

 Understanding

2.76

understood

2.76

Activations Density 0.071%

terms related to understanding and comprehension

No Comments

No Known Activations